Dissertations / Theses: 'Unsupervised neural networks'

1

Nyamapfene, Abel. "Unsupervised multimodal neural networks." Thesis, University of Surrey, 2006. http://epubs.surrey.ac.uk/844064/.

Full text

Abstract:

We extend the in-situ Hebbian-linked SOMs network by Miikkulainen to come up with two unsupervised neural networks that learn the mapping between the individual modes of a multimodal dataset. The first network, the single-pass Hebbian linked SOMs network, extends the in-situ Hebbian-linked SOMs network by enabling the Hebbian link weights to be computed through one- shot learning. The second network, a modified counter propagation network, extends the unsupervised learning of crossmodal mappings by making it possible for only one self-organising map to implement the crossmodal mapping. The two proposed networks each have a smaller computation time and achieve lower crossmodal mean squared errors than the in-situ Hebbian- linked SOMs network when assessed on two bimodal datasets, an audio-acoustic speech utterance dataset and a phonological-semantics child utterance dataset. Of the three network architectures, the modified counterpropagation network achieves the highest percentage of correct classifications comparable to that of the LVQ-2 algorithm by Kohonen and the neural network for category learning by de Sa and Ballard in classification tasks using the audio-acoustic speech utterance dataset. To facilitate multimodal processing of temporal data, we propose a Temporal Hypermap neural network architecture that learns and recalls multiple temporal patterns in an unsupervised manner. The Temporal Hypermap introduces flexibility in the recall of temporal patterns - a stored temporal pattern can be retrieved by prompting the network with the temporal pattern's identity vector, whilst the incorporation of short term memory allows the recall of a temporal pattern, starting from the pattern item specified by contextual information up to the last item in the pattern sequence. Finally, we extend the connectionist modelling of child language acquisition in two important respects. First, we introduce the concept of multimodal representation of speech utterances at the one-word and two-word stage. This allows us to model child language at the one-word utterance stage with a single modified counterpropagation network, which is an improvement on previous models in which multiple networks are required to simulate the different aspects of speech at the one-word utterance stage. Secondly, we present, for the time, a connectionist model of the transition of child language from the one-word utterance stage to the two-word utterance stage. We achieve this using a gated multi-net comprising a modified counterpropagation network and a Temporal Hypermap.

APA, Harvard, Vancouver, ISO, and other styles

2

Macdonald, Donald. "Unsupervised neural networks for visualisation of data." Thesis, University of the West of Scotland, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.395687.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Berry, Ian Michael. "Data classification using unsupervised artificial neural networks." Thesis, University of Sussex, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.390079.

Full text

APA, Harvard, Vancouver, ISO, and other styles

4

Harpur, George Francis. "Low entropy coding with unsupervised neural networks." Thesis, University of Cambridge, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.627227.

Full text

APA, Harvard, Vancouver, ISO, and other styles

5

Walcott, Terry Hugh. "Market prediction for SMEs using unsupervised neural networks." Thesis, University of East London, 2009. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.532991.

Full text

Abstract:

The objective of this study was to create a market prediction model for small and medium enterprises (SMEs). To achieve this, an extensive literature examination was carried out which focused on SMEs, marketing and prediction; neural networks as a competitive tool for SME marketing; and clustering a review. A Delphi study was used for collating expert opinions in order to determine likely factors hindering SMEs wanting to remain business proficient. An analysis of Delphi responses led to the creation of a market prediction questionnaire. This questionnaire was used to create variables for analysis using four unsupervised algorithm. The algorithms used in this study were joining tree, k-means, learning vector quantisation and the snap-drift algorithm. Questionnaire data took the form of data collected from 102 SMEs. This led to the determination of 23 variables that could best represent the data under examination. Further analysis of each 23 variable led to the choice of respondents for case study analysis. A higher education college (HEC) and a private hire company (PHC) were chosen for this stage of the research. In case study one (1), analysis has discovered that HEC's can compete with Universities if they tailor their products and services to selected academic markets as opposed to entering all academic sectors. The findings suggest that if a HEC monitors the growth of its students and establishes the likely point of creating new courses they will retain students and not lose them to universities. Comparisons between the case HEC and rival HECs has demonstrated that there is a knowledge gap that currently exists between these institutions and by using post-modem marketing coupled with neural networks a competitive advantage will be realised. In case study two (2), a private hire company was investigated allowing for the interpretation of current markets for this firm by making existing operating areas more transparent. Therefore, knowledge barriers were discovered between telephonists and drivers, and the owner/manger and drivers. As such historical data was used for distinguishing the performance of drivers within this firm. In differentiating job times and driver performance our case organisation was better equipped for determining the times in which it is most busy. Therefore, being able to determine the amount of telephonists needed per shift and the likely busy periods in which this firm will operate. Analysis of all participating SMEs have revealed that: (1) these firms are more likely to fail in the first two years of operation generally, (2) successful SMEs are owned or managed by persons having prior management and or general business expertise, (3) success is normally attributed to experience gained as a result of working or managing a threatened firm in the past, (4) successful SMEs understand the importance of valuing the ethnicity held in their respective firms and (5) these firms are less likely to understand how technology can aid and sustain market growth generally. It seems market prediction in SMEs can be affected by employee performance and managerial ability to undertake predefined tasks. The findings suggest that there are SMEs that can benefit from market prediction. More importantly, the findings indicate the need to understand the SME for determining the types of intelligent systems that can be used for initiate marketing and providing marketing prediction generally. Several theoretical and practical implications are discussed. To this effect, SME owner/managers, researchers in academia, government and public SME organisations can learn from the results. Suggestions for future research are also presented.

APA, Harvard, Vancouver, ISO, and other styles

6

Vetcha, Sarat Babu. "Fault diagnosis in pumps by unsupervised neural networks." Thesis, University of Sussex, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.300604.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Bishop, Griffin R. "Unsupervised Semantic Segmentation through Cross-Instance Representation Similarity." Digital WPI, 2020. https://digitalcommons.wpi.edu/etd-theses/1371.

Full text

Abstract:

Semantic segmentation methods using deep neural networks typically require huge volumes of annotated data to train properly. Due to the expense of collecting these pixel-level dataset annotations, the problem of semantic segmentation without ground-truth labels has been recently proposed. Many current approaches to unsupervised semantic segmentation frame the problem as a pixel clustering task, and in particular focus heavily on color differences between image regions. In this paper, we explore a weakness to this approach: By focusing on color, these approaches do not adequately capture relationships between similar objects across images. We present a new approach to the problem, and propose a novel architecture that captures the characteristic similarities of objects between images directly. We design a synthetic dataset to illustrate this flaw in an existing model. Experiments on this synthetic dataset show that our method can succeed where the pixel color clustering approach fails. Further, we show that plain autoencoder models can implicitly capture these cross-instance object relationships. This suggests that some generative model architectures may be viable candidates for unsupervised semantic segmentation even with no additional loss terms.

APA, Harvard, Vancouver, ISO, and other styles

8

Plumbley, Mark David. "An information-theoretic approach to unsupervised connectionist models." Thesis, University of Cambridge, 1991. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.387051.

Full text

APA, Harvard, Vancouver, ISO, and other styles

9

Galtier, Mathieu. "A mathematical approach to unsupervised learning in recurrent neural networks." Paris, ENMP, 2011. https://pastel.hal.science/pastel-00667368.

Full text

Abstract:

Dans cette thèse nous tentons de donner un sens mathématique à la proposition : le néocortex se construit un modèle de son environnement. Nous considérons que le néocortex est un réseau de neurones spikants dont la connectivité est soumise à une lente évolution appelée apprentissage. Dans le cas où le nombre de neurones est proche de l'infini, nous proposons une nouvelle méthode de champ-moyen afin de trouver une équation décrivant l'évolution du taux de décharge de populations de neurones. Nous étudions donc la dynamique de ce système moyennisé avec apprentissage. Dans le régime où l'apprentissage est beaucoup plus lent que l'activité du réseau nous pouvons utiliser des outils de moyennisation temporelle pour les systèmes lents/rapides. Dans ce cadre mathématique nous montrons que la connectivité du réseau converge toujours vers une unique valeur d'équilibre que nous pouvons calculer explicitement. Cette connectivité regroupe l'ensemble des connaissances du réseau à propos de son environnement. Nous comparons cette connectivité à l'équilibre avec les stimuli du réseau. Considérant que l'environnement est solution d'un système dynamique quelconque, il est possible de montrer que le réseau encode la totalité de l'information nécessaire à la définition de ce système dynamique. En effet nous montrons que la partie symétrique de la connectivité correspond à la variété sur laquelle est définie le système dynamique de l'environnement, alors que la partie anti-symétrique de la connectivité correspond au champ de vecteur définissant le système dynamique de l'environnement. Dans ce contexte il devient clair que le réseau agit comme un prédicteur de son environnement
In this thesis, we propose to give a mathematical sense to the claim: the neocortex builds itself a model of its environment. We study the neocortex as a network of spiking neurons undergoing slow STDP learning. By considering that the number of neurons is close to infinity, we propose a new mean-field method to find the ''smoother'' equation describing the firing-rate of populations of these neurons. Then, we study the dynamics of this averaged system with learning. By assuming the modification of the synapses' strength is very slow compared the activity of the network, it is possible to use tools from temporal averaging theory. They lead to showing that the connectivity of the network always converges towards a single equilibrium point which can be computed explicitely. This connectivity gathers the knowledge of the network about the world. Finally, we analyze the equilibrium connectivity and compare it to the inputs. By seeing the inputs as the solution of a dynamical system, we are able to show that the connectivity embedded the entire information about this dynamical system. Indeed, we show that the symmetric part of the connectivity leads to finding the manifold over which the inputs dynamical system is defined, and that the anti-symmetric part of the connectivity corresponds to the vector field of the inputs dynamical system. In this context, the network acts as a predictor of the future events in its environment

APA, Harvard, Vancouver, ISO, and other styles

10

Haddad, Josef, and Carl Piehl. "Unsupervised anomaly detection in time series with recurrent neural networks." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-259655.

Full text

Abstract:

Artificial neural networks (ANN) have been successfully applied to a wide range of problems. However, most of the ANN-based models do not attempt to model the brain in detail, but there are still some models that do. An example of a biologically constrained ANN is Hierarchical Temporal Memory (HTM). This study applies HTM and Long Short-Term Memory (LSTM) to anomaly detection problems in time series in order to compare their performance for this task. The shape of the anomalies are restricted to point anomalies and the time series are univariate. Pre-existing implementations that utilise these networks for unsupervised anomaly detection in time series are used in this study. We primarily use our own synthetic data sets in order to discover the networks’ robustness to noise and how they compare to each other regarding different characteristics in the time series. Our results shows that both networks can handle noisy time series and the difference in performance regarding noise robustness is not significant for the time series used in the study. LSTM outperforms HTM in detecting point anomalies on our synthetic time series with sine curve trend but a conclusion about the overall best performing network among these two remains inconclusive.
Artificiella neurala nätverk (ANN) har tillämpats på många problem. Däremot försöker inte de flesta ANN-modeller efterlikna hjärnan i detalj. Ett exempel på ett ANN som är begränsat till att efterlikna hjärnan är Hierarchical Temporal Memory (HTM). Denna studie tillämpar HTM och Long Short-Term Memory (LSTM) på avvikelsedetektionsproblem i tidsserier för att undersöka vilka styrkor och svagheter de har för detta problem. Avvikelserna i denna studie är begränsade till punktavvikelser och tidsserierna är i endast en variabel. Redan existerande implementationer som utnyttjar dessa nätverk för oövervakad avvikelsedetektionsproblem i tidsserier används i denna studie. Vi använder främst våra egna syntetiska tidsserier för att undersöka hur nätverken hanterar brus och hur de hanterar olika egenskaper som en tidsserie kan ha. Våra resultat visar att båda nätverken kan hantera brus och prestationsskillnaden rörande brusrobusthet var inte tillräckligt stor för att urskilja modellerna. LSTM presterade bättre än HTM på att upptäcka punktavvikelser i våra syntetiska tidsserier som följer en sinuskurva men en slutsats angående vilket nätverk som presterar bäst överlag är fortfarande oavgjord.

APA, Harvard, Vancouver, ISO, and other styles

11

Zeltner, Felix. "Autonomous Terrain Classification Through Unsupervised Learning." Thesis, Luleå tekniska universitet, Institutionen för system- och rymdteknik, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-60893.

Full text

Abstract:

A key component of autonomous outdoor navigation in unstructured environments is the classification of terrain. Recent development in the area of machine learning show promising results in the task of scene segmentation but are limited by the labels used during their supervised training. In this work, we present and evaluate a flexible strategy for terrain classification based on three components: A deep convolutional neural network trained on colour, depth and infrared data which provides feature vectors for image segmentation, a set of exchangeable segmentation engines that operate in this feature space and a novel, air pressure based actuator responsible for distinguishing rigid obstacles from those that only appear as such. Through the use of unsupervised learning we eliminate the need for labeled training data and allow our system to adapt to previously unseen terrain classes. We evaluate the performance of this classification scheme on a mobile robot platform in an environment containing vegetation and trees with a Kinect v2 sensor as low-cost depth camera. Our experiments show that the features generated by our neural network are currently not competitive with state of the art implementations and that our system is not yet ready for real world applications.

APA, Harvard, Vancouver, ISO, and other styles

12

Mohammed, Derek. "A Comparative Study of Unsupervised Neural Networks in Detecting Financial Misstatements." NSUWorks, 2005. http://nsuworks.nova.edu/gscis_etd/730.

Full text

Abstract:

Financial misstatements have plagued the financial world for several decades. However they have increased in frequency and affected more stockholders and stakeholders in recent years. This intensity of occurrence has prompted the need for more fraud detecting methods from auditors and government regulators alike. Traditionally, statistical models have been utilized in detecting financial misstatements. However, these statistical models are based on assumptions, such as a log-linear relation among the independent variables, which are not applicable to financial data. Artificial neural networks are not bounded by the limitations affecting statistical models, and have been found to give robust results when applied to classification problems. The purpose of study was to compare unsupervised neural networks, the Nonlinear Principal Component Analysis (NLPCA) network and the Kohonen Self-Organizing Map (SOM), in detecting financial misstatements. As a performance benchmark, the results from the NLPCA and SOM networks were compared to the traditional statistical method, the logit model. The dataset used in this study consisted of firms who issued financial statements for the period 1990 to 2005. The dataset was limited to firms from the computer-technology industry and financial services sectors, and whose annual financial statements were publicly available. Using the matched-pair approach, each fraud firm was paired with a similar non-fraud firm based on industry, time period and size. Unlike the Logit model, the NLPCA and SOM models required the determination of several parameters. The configurations for the NLPCA and SOM models were found experimentally. In order to attain a true comparison between the NLPCA, SOM and Logit models, both training and testing for the models were done with the same samples. Using different metrics for comparison it was found that the NLPCA and SOM models were effective in detecting financial misstatements. It was also determined that these unsupervised neural networks produced better classification accuracies than the Logit model. Additionally, the NLPCA model, which is based on correlational learning, marginally outperformed the SOM model, which is based on competitive learning. The results from this study support future use of NLPCA and SOM as assessment tools in detecting financial misstatements.

APA, Harvard, Vancouver, ISO, and other styles

13

Manne, Mihira. "MACHINE VISION FOR AUTOMATICVISUAL INSPECTION OF WOODENRAILWAY SLEEPERS USING UNSUPERVISED NEURAL NETWORKS." Thesis, Högskolan Dalarna, Datateknik, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:du-3977.

Full text

Abstract:

The motivation for this thesis work is the need for improving reliability of equipment and quality of service to railway passengers as well as a requirement for cost-effective and efficient condition maintenance management for rail transportation. This thesis work develops a fusion of various machine vision analysis methods to achieve high performance in automation of wooden rail track inspection.The condition monitoring in rail transport is done manually by a human operator where people rely on inference systems and assumptions to develop conclusions. The use of conditional monitoring allows maintenance to be scheduled, or other actions to be taken to avoid the consequences of failure, before the failure occurs. Manual or automated condition monitoring of materials in fields of public transportation like railway, aerial navigation, traffic safety, etc, where safety is of prior importance needs non-destructive testing (NDT).In general, wooden railway sleeper inspection is done manually by a human operator, by moving along the rail sleeper and gathering information by visual and sound analysis for examining the presence of cracks. Human inspectors working on lines visually inspect wooden rails to judge the quality of rail sleeper. In this project work the machine vision system is developed based on the manual visual analysis system, which uses digital cameras and image processing software to perform similar manual inspections. As the manual inspection requires much effort and is expected to be error prone sometimes and also appears difficult to discriminate even for a human operator by the frequent changes in inspected material. The machine vision system developed classifies the condition of material by examining individual pixels of images, processing them and attempting to develop conclusions with the assistance of knowledge bases and features.A pattern recognition approach is developed based on the methodological knowledge from manual procedure. The pattern recognition approach for this thesis work was developed and achieved by a non destructive testing method to identify the flaws in manually done condition monitoring of sleepers.In this method, a test vehicle is designed to capture sleeper images similar to visual inspection by human operator and the raw data for pattern recognition approach is provided from the captured images of the wooden sleepers. The data from the NDT method were further processed and appropriate features were extracted.The collection of data by the NDT method is to achieve high accuracy in reliable classification results. A key idea is to use the non supervised classifier based on the features extracted from the method to discriminate the condition of wooden sleepers in to either good or bad. Self organising map is used as classifier for the wooden sleeper classification.In order to achieve greater integration, the data collected by the machine vision system was made to interface with one another by a strategy called fusion. Data fusion was looked in at two different levels namely sensor-level fusion, feature- level fusion. As the goal was to reduce the accuracy of the human error on the rail sleeper classification as good or bad the results obtained by the feature-level fusion compared to that of the results of actual classification were satisfactory.

APA, Harvard, Vancouver, ISO, and other styles

14

Suits, David B. "A simplified drive-reinforcement model for unsupervised learning in artificial neural networks /." Online version of thesis, 1992. http://hdl.handle.net/1850/11087.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Yang, Li. "Biologically inspired visual models by sparse and unsupervised learning : a dissertation /." Full text open access at:, 2007. http://content.ohsu.edu/u?/etd,163.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Geigel, Arturo. "Unsupervised Learning Trojan." NSUWorks, 2014. http://nsuworks.nova.edu/gscis_etd/17.

Full text

Abstract:

This work presents a proof of concept of an Unsupervised Learning Trojan. The Unsupervised Learning Trojan presents new challenges over previous work on the Neural network Trojan, since the attacker does not control most of the environment. The current work will presented an analysis of how the attack can be successful by proposing new assumptions under which the attack can become a viable one. A general analysis of how the compromise can be theoretically supported is presented, providing enough background for practical implementation development. The analysis was carried out using 3 selected algorithms that can cover a wide variety of circumstances of unsupervised learning. A selection of 4 encoding schemes on 4 datasets were chosen to represent actual scenarios under which the Trojan compromise might be targeted. A detailed procedure is presented to demonstrate the attack's viability under assumed circumstances. Two tests of hypothesis concerning the experimental setup were carried out which yielded acceptance of the null hypothesis. Further discussion is contemplated on various aspects of actual implementation issues and real world scenarios where this attack might be contemplated.

APA, Harvard, Vancouver, ISO, and other styles

17

Abidogun, Olusola Adeniyi. "Data mining, fraud detection and mobile telecommunications: call pattern analysis with unsupervised neural networks." Thesis, University of the Western Cape, 2005. http://etd.uwc.ac.za/index.php?module=etd&amp.

Full text

Abstract:

Huge amounts of data are being collected as a result of the increased use of mobile telecommunications. Insight into information and knowledge derived from these databases can give operators a competitive edge in terms of customer care and retention,
marketing and fraud detection. One of the strategies for fraud detection checks for signs of questionable changes in user behavior. Although the intentions of the mobile phone users cannot be observed, their intentions are reflected in the call data which define usage patterns. Over a period of time, an individual phone generates a large pattern of use. While call data are recorded for subscribers for billing purposes, we are making no prior assumptions about the data indicative of fraudulent call patterns, i.e. the calls made for billing purpose are unlabeled. Further analysis is thus, required to be able to isolate fraudulent usage. An unsupervised learning algorithm can analyse and cluster call patterns for each subscriber in order to facilitate the fraud detection process.

This research investigates the unsupervised learning potentials of two neural networks for the profiling of calls made by users over a period of time in a mobile telecommunication network. Our study provides a comparative analysis and application of Self-Organizing Maps (SOM) and Long Short-Term Memory (LSTM) recurrent neural networks algorithms to user call data records in order to conduct a descriptive data mining on users call patterns.

Our investigation shows the learning ability of both techniques to discriminate user call patterns
the LSTM recurrent neural network algorithm providing a better discrimination than the SOM algorithm in terms of long time series modelling. LSTM discriminates different types of temporal sequences and groups them according to a variety of features. The ordered features can later be interpreted and labeled according to specific requirements of the mobile service provider. Thus, suspicious call behaviours are isolated within the mobile telecommunication network and can be used to to identify fraudulent call patterns. We give results using masked call data
from a real mobile telecommunication network.

APA, Harvard, Vancouver, ISO, and other styles

18

Charles, Eugene Yougarajah Andrew. "Supervised and unsupervised weight and delay adaptation learning in temporal coding spiking neural networks." Thesis, Cardiff University, 2006. http://orca.cf.ac.uk/56168/.

Full text

Abstract:

Artificial neural networks are learning paradigms which mimic the biological neural system. The temporal coding Spiking Neural Network, a relatively new artificial neural network paradigm, is considered to be computationally more powerful than the conventional neural network. Research on the network of spiking neurons is an emerging field and has potential for wider investigation. This research explores alternative learning models with temporal coding spiking neural networks for clustering and classification tasks. Neurons are known to be operating in two modes namely, as integrators and coincidence detectors. Previous temporal coding spiking neural networks, realising spiking neurons as integrators, were utilised for analytical studies. Temporal coding spiking neural networks applied successfully for clustering and classification tasks realised spiking neurons as coincidence detectors and encoded input in formation in the connection delays through a weight adaptation technique. These learning models select suitably delayed connections by enhancing the weights of those connections while weakening the others. This research investigates the learning in temporal coding spiking neural networks with spiking neurons as integrators and coincidence detectors. Focus is given to both supervised and unsupervised learning through weight as well as through delay adaptation. Three novel models for learning in temporal coding spiking neural networks are presented in this research. The first spiking neural network model, Self- Organising Weight Adaptation Spiking Neural Network (SOWA_SNN) realises the spiking neuron as integrator. This model adapts and encodes input information in its connection weights. The second learning model, Self-Organising Delay Adaptation Spiking Neural Network (SODA_SNN) and the third model, Super vised Delay Adaptation Spiking Neural Network (SDA_SNN) realise the spiking neuron as coincidence detector. These two models adapt the connection delays in order to detect temporal patterns through coincidence detection. The first two models were developed for clustering applications and the third for classification tasks. All three models employ Hebbian-based learning rules to update the network connection parameters by utilising the difference between the input and output spike times. The proposed temporal coding spiking neural network models were implemented as discrete models in software and their characteristics and capabilities were analysed through simulations on three bench mark data sets and a high dimensional data set. All three models were able to cluster or classify the analysed data sets efficiently with a high degree of accuracy. The performance of the proposed models, was found to be better than the existing spiking neural network models as well as conventional neural networks. The proposed learning paradigms could be applied to a wide range of applications including manufacturing, business and biomedical domains.

APA, Harvard, Vancouver, ISO, and other styles

19

Chavez, Wesley. "An Exploration of Linear Classifiers for Unsupervised Spiking Neural Networks with Event-Driven Data." PDXScholar, 2018. https://pdxscholar.library.pdx.edu/open_access_etds/4439.

Full text

Abstract:

Object recognition in video has seen giant strides in accuracy improvements in the last few years, a testament to the computational capacity of deep convolutional neural networks. However, this computational capacity of software-based neural networks coincides with high power consumption compared to that of some spiking neural networks (SNNs), up to 300,000 times more energy per synaptic event in IBM's TrueNorth chip, for example. SNNs are also well-suited to exploit the precise timing of event-driven image sensors, which transmit asynchronous "events" only when the luminance of a pixel changes above or below a threshold value. The combination of event-based imagers and SNNs becomes a straightforward way to achieve low power consumption in object recognition tasks. This thesis compares different linear classifiers for two low-power, hardware-friendly, spiking, unsupervised neural network architectures, SSLCA and HFirst, in response to asynchronous event-based data, and explores their ability to learn and recognize patterns from two event-based image datasets, N-MNIST and CIFAR10-DVS. By performing a grid search of important SNN and classifier hyperparameters, we also explore how to improve classification performance of these architectures. Results show that a softmax regression classifier exhibits modest accuracy gains (0.73%) over the next-best performing linear support vector machine (SVM), and considerably outperforms a single layer perceptron (by 5.28%) when classification performance is averaged over all datasets and spiking neural network architectures with varied hyperparameters. Min-max normalization of the inputs to the linear classifiers aides in classification accuracy, except in the case of the single layer perceptron classifier. We also see the highest reported classification accuracy for spiking convolutional networks on N-MNIST and CIFAR10-DVS, increasing this accuracy from 97.77% to 97.82%, and 29.67% to 31.76%, respectively. These findings are relevant for any system employing unsupervised SNNs to extract redundant features from event-driven data for recognition.

APA, Harvard, Vancouver, ISO, and other styles

20

Nikbakht, Silab Rasoul. "Unsupervised learning for parametric optimization in wireless networks." Doctoral thesis, Universitat Pompeu Fabra, 2021. http://hdl.handle.net/10803/671246.

Full text

Abstract:

This thesis studies parametric optimization in cellular and cell-free networks, exploring data-based and expert-based paradigms. Power allocation and power control, which adjust the transmit power to meet different fairness criteria such as max-min or max-product, are crucial tasks in wireless communications that fall into the parametric optimization category. The state-of-the-art approaches for power control and power allocation often demand huge computational costs and are not suitable for real-time applications. To address this issue, we develop a general-purpose unsupervised-learning approach for solving parametric optimizations; and extend the well-known fractional power control algorithm. In the data-based paradigm, we create an unsupervised learning framework that defines a custom neural network (NN), incorporating expert knowledge to the NN loss function to solve the power control and power allocation problems. In this approach, a feedforward NN is trained by repeatedly sampling the parameter space, but, rather than solving the associated optimization problem completely, a single step is taken along the gradient of the objective function. The resulting method is applicable for both convex and non-convex optimization problems. It offers two-to-three orders of magnitude speedup in the power control and power allocation problems compared to a convex solver—whenever appliable. In the expert-driven paradigm, we investigate the extension of fractional power control to cell-free networks. The resulting closed-form solution can be evaluated for uplink and downlink effortlessly and reaches an (almost) optimum solution in the uplink case. In both paradigms, we place a particular focus on large scale gains—the amount of attenuation experienced by the local-average received power. The slow-varying nature of the large-scale gains relaxes the need for a frequent update of the solutions in both the data-driven and expert-driven paradigms, enabling real-time application for both methods.
Aqueta tesis estudia l’optimització paramètrica a les xarxes cel.lulars i xarxes cell-free, explotant els paradigmes basats en dades i basats en experts. L’assignació i control de la potencia, que ajusten la potencia de transmissió per complir amb diferents criteris d’equitat com max-min o max-product, son tasques crucials en les telecomunicacions inalàmbriques pertanyents a la categoria d’optimització paramètrica. Les tècniques d’última generació per al control i assignació de la potència solen exigir enormes costos computacionals i no son adequats per aplicacions en temps real. Per abordar aquesta qüestió, desenvolupem una tècnica de propòsit general utilitzant aprenentatge no supervisat per resoldre optimitzacions paramètriques; i al mateix temps ampliem el reconegut algoritme de control de potencia fraccionada. En el paradigma basat en dades, creem un marc d’aprenentatge no supervisat que defineix una xarxa neuronal (NN, sigles de Neural Network en Anglès) especifica, incorporant coneixements experts a la funció de cost de la NN per resoldre els problemes de control i assignació de potència. Dins d’aquest enfocament, s’entrena una NN de tipus feedforward mitjançant el mostreig repetit en l’espai de paràmetres, però, en lloc de resoldre completament el problema d’optimització associat, es pren un sol pas en la direcció del gradient de la funció objectiu. El mètode resultant ´es aplicable tant als problemes d’optimització convexos com no convexos. Això ofereix una acceleració de dos a tres ordres de magnitud en els problemes de control i assignació de potencia en comparació amb un algoritme de resolució convexa—sempre que sigui aplicable. En el paradigma dirigit per experts, investiguem l’extensió del control de potencia fraccionada a les xarxes sense cèl·lules. La solució tancada resultant pot ser avaluada per a l’enllaç de pujada i el de baixada sense esforç i assoleix una solució (gaire) òptima en el cas de l’enllaç de pujada. En ambdós paradigmes, ens centrem especialment en els guanys a gran escala—la quantitat d’atenuació que experimenta la potencia mitja local rebuda. La naturalesa de variació lenta dels guanys a gran escala relaxa la necessitat d’una actualització freqüent de les solucions tant en el paradigma basat en dades com en el basat en experts, permetent d’aquesta manera l’ús dels dos mètodes en aplicacions en temps real.
Esta tesis estudia la optimización paramétrica en las redes celulares y redes cell-free, explorando los paradigmas basados en datos y en expertos. La asignación y el control de la potencia, que ajustan la potencia de transmisión para cumplir con diferentes criterios de equidad como max-min o max-product, son tareas cruciales en las comunicaciones inalámbricas pertenecientes a la categoría de optimización paramétrica. Los enfoques más modernos de control y asignación de la potencia suelen exigir enormes costes computacionales y no son adecuados para aplicaciones en tiempo real. Para abordar esta cuestión, desarrollamos un enfoque de aprendizaje no supervisado de propósito general que resuelve las optimizaciones paramétricas y a su vez ampliamos el reconocido algoritmo de control de potencia fraccionada. En el paradigma basado en datos, creamos un marco de aprendizaje no supervisado que define una red neuronal (NN, por sus siglas en inglés) específica, incorporando conocimiento de expertos a la función de coste de la NN para resolver los problemas de control y asignación de potencia. Dentro de este enfoque, se entrena una NN de tipo feedforward mediante el muestreo repetido del espacio de parámetros, pero, en lugar de resolver completamente el problema de optimización asociado, se toma un solo paso en la dirección del gradiente de la función objetivo. El método resultante es aplicable tanto a los problemas de optimización convexos como no convexos. Ofrece una aceleración de dos a tres órdenes de magnitud en los problemas de control y asignación de potencia, en comparación con un algoritmo de resolución convexo—siempre que sea aplicable. Dentro del paradigma dirigido por expertos, investigamos la extensión del control de potencia fraccionada a las redes cell-free. La solución de forma cerrada resultante puede ser evaluada para el enlace uplink y el downlink sin esfuerzo y alcanza una solución (casi) óptima en el caso del enlace uplink. En ambos paradigmas, nos centramos especialmente en las large-scale gains— la cantidad de atenuación que experimenta la potencia media local recibida. La naturaleza lenta y variable de las ganancias a gran escala relaja la necesidad de una actualización frecuente de las soluciones tanto en el paradigma basado en datos como en el basado en expertos, permitiendo el uso de ambos métodos en aplicaciones en tiempo real.

APA, Harvard, Vancouver, ISO, and other styles

21

Vendramin, Nicoló. "Unsupervised Anomaly Detection on Multi-Process Event Time Series." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-254885.

Full text

Abstract:

Establishing whether the observed data are anomalous or not is an important task that has been widely investigated in literature, and it becomes an even more complex problem if combined with high dimensional representations and multiple sources independently generating the patterns to be analyzed. The work presented in this master thesis employs a data-driven pipeline for the definition of a recurrent auto-encoder architecture to analyze, in an unsupervised fashion, high-dimensional event time-series generated by multiple and variable processes interacting with a system. Facing the above mentioned problem the work investigates whether it is possible or not to use a single model to analyze patterns produced by different sources. The analysis of log files that record events of interaction between users and the radio network infrastructure is employed as realworld case-study for the given problem. The investigation aims to verify the performances of a single machine learning model applied to the learning of multiple patterns developed through time by distinct sources. The work proposes a pipeline, to deal with the complex representation of the data source and the definition and tuning of the anomaly detection model, that is based on no domain-specific knowledge and can thus be adapted to different problem settings. The model has been implemented in four different variants that have been evaluated over both normal and anomalous data, gathered partially from real network cells and partially from the simulation of anomalous behaviours. The empirical results show the applicability of the model for the detection of anomalous sequences and events in the described conditions, with scores reaching above 80% in terms of F1-score, and varying depending on the specific threshold setting. In addition, their deeper interpretation gives insights about the difference between the variants of the model and thus, their limitations and strong points.
Att fastställa huruvida observerade data är avvikande eller inte är en viktig uppgift som har studerats ingående i litteraturen och problemet blir ännu mer komplext, om detta kombineras med högdimensionella representationer och flera källor som oberoende genererar de mönster som ska analyseras. Arbetet som presenteras i denna uppsats använder en data-driven pipeline för definitionen av en återkommande auto-encoderarkitektur för att analysera, på ett oövervakat sätt, högdimensionella händelsetidsserier som genereras av flera och variabla processer som interagerar med ett system. Mot bakgrund av ovanstående problem undersöker arbetet om det är möjligt eller inte att använda en enda modell för att analysera mönster som producerats av olika källor. Analys av loggfiler som registrerar händelser av interaktion mellan användare och radionätverksinfrastruktur används som en fallstudie för det angivna problemet. Undersökningen syftar till att verifiera prestandan hos en enda maskininlärningsmodell som tillämpas för inlärning av flera mönster som utvecklats över tid från olika källor. Arbetet föreslår en pipeline för att hantera den komplexa representationen hos datakällorna och definitionen och avstämningen av anomalidetektionsmodellen, som inte är baserad på domänspecifik kunskap och därför kan anpassas till olika probleminställningar. Modellen har implementerats i fyra olika varianter som har utvärderats med avseende på både normala och avvikande data, som delvis har samlats in från verkliga nätverksceller och delvis från simulering av avvikande beteenden. De empiriska resultaten visar modellens tillämplighet för detektering av avvikande sekvenser och händelser i det föreslagna ramverket, med F1-score över 80%, varierande beroende på den specifika tröskelinställningen. Dessutom ger deras djupare tolkning insikter om skillnaden mellan olika varianter av modellen och därmed deras begränsningar och styrkor.

APA, Harvard, Vancouver, ISO, and other styles

22

Ayodele, Taiwo Oladipupo. "An integrated framework for solving email management problems with unsupervised machine learning techniques and artificial neural networks." Thesis, University of Portsmouth, 2010. https://researchportal.port.ac.uk/portal/en/theses/an-integrated-framework-for-solving-email-management-problems-with-unsupervised-machine-learning-techniques-and-artificial-neural-networks(7bb647da-3759-47e2-812a-e1adc5e36af0).html.

Full text

Abstract:

The volume of email being received by email users nowadays is enormous. Email users spend significant amount of time to manage their emails, which tends to be tedious. The task of grouping emails for further processing often discourages users from filing their mail, resulting in unmanageable mailboxes that contain hundreds or even thousands of unsorted messages. The present work starts by redeveloping a systematic framework of email management. Major email managing tasks were identified, investigated and classified into categories, namely, email summarisation, email grouping and email urgency reply prediction, the details of which are provided within this research work. Any possible solution to problems of managing emails, such as email overloads and email congestions should eliminate the need for human intuition in email management systems. Hence this work focuses on utilising unsupervised machine learning techniques in the development of key email management tools such as adaptive mail summa riser, which provide precise summaries of email messages, a mail cluster, which groups email messages based on the focus of the mail and a mail predictor, which determines mails that need attention or require urgent replies. This work was carried out in different stages. First, an unsupervised mail summariser learner was proposed and developed, that utilises knowledge, as well as words and phrases modelling (keywords extractions) approach to provide a coherent email summaries. Secondly, the task of grouping emails into categories based on the focus of the mail contents is explored. Email evolving clustering method was developed to organise mails into relevant and accurate clusters, resulting in a clustering similarity matrix. Artificial neural networks with back propagation techniques were involved. Thirdly, a reply prediction technique was proposed for the purpose of classifying mail into different reply urgency index by exploiting the unsupervised learning with human justifications in the early phase. The research work eventually integrates all three into an email management system. An email management toolkit was then developed to test, evaluate and illustrate the proposed email management system. The prototype toolkit can be organised as a plug-in for most of email clients. A largescale case study was conducted in which the effectiveness of the systematic email management framework developed in this work was demonstrated.

APA, Harvard, Vancouver, ISO, and other styles

23

Kilinc, Ismail Ozsel. "Graph-based Latent Embedding, Annotation and Representation Learning in Neural Networks for Semi-supervised and Unsupervised Settings." Scholar Commons, 2017. https://scholarcommons.usf.edu/etd/7415.

Full text

Abstract:

Machine learning has been immensely successful in supervised learning with outstanding examples in major industrial applications such as voice and image recognition. Following these developments, the most recent research has now begun to focus primarily on algorithms which can exploit very large sets of unlabeled examples to reduce the amount of manually labeled data required for existing models to perform well. In this dissertation, we propose graph-based latent embedding/annotation/representation learning techniques in neural networks tailored for semi-supervised and unsupervised learning problems. Specifically, we propose a novel regularization technique called Graph-based Activity Regularization (GAR) and a novel output layer modification called Auto-clustering Output Layer (ACOL) which can be used separately or collaboratively to develop scalable and efficient learning frameworks for semi-supervised and unsupervised settings. First, singularly using the GAR technique, we develop a framework providing an effective and scalable graph-based solution for semi-supervised settings in which there exists a large number of observations but a small subset with ground-truth labels. The proposed approach is natural for the classification framework on neural networks as it requires no additional task calculating the reconstruction error (as in autoencoder based methods) or implementing zero-sum game mechanism (as in adversarial training based methods). We demonstrate that GAR effectively and accurately propagates the available labels to unlabeled examples. Our results show comparable performance with state-of-the-art generative approaches for this setting using an easier-to-train framework. Second, we explore a different type of semi-supervised setting where a coarse level of labeling is available for all the observations but the model has to learn a fine, deeper level of latent annotations for each one. Problems in this setting are likely to be encountered in many domains such as text categorization, protein function prediction, image classification as well as in exploratory scientific studies such as medical and genomics research. We consider this setting as simultaneously performed supervised classification (per the available coarse labels) and unsupervised clustering (within each one of the coarse labels) and propose a novel framework combining GAR with ACOL, which enables the network to perform concurrent classification and clustering. We demonstrate how the coarse label supervision impacts performance and the classification task actually helps propagate useful clustering information between sub-classes. Comparative tests on the most popular image datasets rigorously demonstrate the effectiveness and competitiveness of the proposed approach. The third and final setup builds on the prior framework to unlock fully unsupervised learning where we propose to substitute real, yet unavailable, parent- class information with pseudo class labels. In this novel unsupervised clustering approach the network can exploit hidden information indirectly introduced through a pseudo classification objective. We train an ACOL network through this pseudo supervision together with unsupervised objective based on GAR and ultimately obtain a k-means friendly latent representation. Furthermore, we demonstrate how the chosen transformation type impacts performance and helps propagate the latent information that is useful in revealing unknown clusters. Our results show state-of-the-art performance for unsupervised clustering tasks on MNIST, SVHN and USPS datasets with the highest accuracies reported to date in the literature.

APA, Harvard, Vancouver, ISO, and other styles

24

Schneider, C. "Using unsupervised machine learning for fault identification in virtual machines." Thesis, University of St Andrews, 2015. http://hdl.handle.net/10023/7327.

Full text

Abstract:

Self-healing systems promise operating cost reductions in large-scale computing environments through the automated detection of, and recovery from, faults. However, at present there appears to be little known empirical evidence comparing the different approaches, or demonstrations that such implementations reduce costs. This thesis compares previous and current self-healing approaches before demonstrating a new, unsupervised approach that combines artificial neural networks with performance tests to perform fault identification in an automated fashion, i.e. the correct and accurate determination of which computer features are associated with a given performance test failure. Several key contributions are made in the course of this research including an analysis of the different types of self-healing approaches based on their contextual use, a baseline for future comparisons between self-healing frameworks that use artificial neural networks, and a successful, automated fault identification in cloud infrastructure, and more specifically virtual machines. This approach uses three established machine learning techniques: Naïve Bayes, Baum-Welch, and Contrastive Divergence Learning. The latter demonstrates minimisation of human-interaction beyond previous implementations by producing a list in decreasing order of likelihood of potential root causes (i.e. fault hypotheses) which brings the state of the art one step closer toward fully self-healing systems. This thesis also examines the impact of that different types of faults have on their respective identification. This helps to understand the validity of the data being presented, and how the field is progressing, whilst examining the differences in impact to identification between emulated thread crashes and errant user changes – a contribution believed to be unique to this research. Lastly, future research avenues and conclusions in automated fault identification are described along with lessons learned throughout this endeavor. This includes the progression of artificial neural networks, how learning algorithms are being developed and understood, and possibilities for automatically generating feature locality data.

APA, Harvard, Vancouver, ISO, and other styles

25

Boschini, Matteo. "Unsupervised Learning of Scene Flow." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/16226/.

Full text

Abstract:

As Computer Vision-powered autonomous systems are increasingly deployed to solve problems in the wild, the case is made for developing visual understanding methods that are robust and flexible. One of the most challenging tasks for this purpose is given by the extraction of scene flow, that is the dense three-dimensional vector field that associates each world point with its corresponding position in the next observed frame, hence describing its three-dimensional motion entirely. The recent addition of a limited amount of ground truth scene flow information to the popular KITTI dataset prompted a renewed interest in the study of techniques for scene flow inference, although the proposed solutions in literature mostly rely on computation-intensive techniques and are characterised by execution times that are not suited for real-time application. In the wake of the recent widespread adoption of Deep Learning techniques to Computer Vision tasks and in light of the convenience of Unsupervised Learning for scenarios in which ground truth collection is difficult and time-consuming, this thesis work proposes the first neural network architecture to be trained in end-to-end fashion for unsupervised scene flow regression from monocular visual data, called Pantaflow. The proposed solution is much faster than currently available state-of-the-art methods and therefore represents a step towards the achievement of real-time scene flow inference.

APA, Harvard, Vancouver, ISO, and other styles

26

Halsey, Phillip A. "The Nature of Modality and Learning Task: Unsupervised Learning of Auditory Categories." Ohio University / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1433406793.

Full text

APA, Harvard, Vancouver, ISO, and other styles

27

Donati, Lorenzo. "Domain Adaptation through Deep Neural Networks for Health Informatics." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2017. http://amslaurea.unibo.it/14888/.

Full text

Abstract:

The PreventIT project is an EU Horizon 2020 project aimed at preventing early functional decline at younger old age. The analysis of causal links between risk factors and functional decline has been made possible by the cooperation of several research institutes' studies. However, since each research institute collects and delivers different kinds of data in different formats, so far the analysis has been assisted by expert geriatricians whose role is to detect the best candidates among hundreds of fields and offer a semantic interpretation of the values. This manual data harmonization approach is very common in both scientific and industrial environments. In this thesis project an alternative method for parsing heterogeneous data is proposed. Since all the datasets represent semantically related data, being all made from longitudinal studies on aging-related metrics, it is possible to train an artificial neural network to perform an automatic domain adaptation. To achieve this goal, a Stacked Denoising Autoencoder has been implemented and trained to extract a domain-invariant representation of the data. Then, from this high-level representation, multiple classifiers have been trained to validate the model and ultimately to predict the probability of functional decline of the patient. This innovative approach to the domain adaptation process can provide an easy and fast solution to many research fields that now rely on human interaction to analyze the semantic data model and perform cross-dataset analysis. Functional decline classifiers show a great improvement in their performance when trained on the domain-invariant features extracted by the Stacked Denoising Autoencoder. Furthermore, this project applies multiple deep neural network classifiers on top of the Stacked Denoising Autoencoder representation, achieving excellent results for the prediction of functional decline in a real case study that involves two different datasets.

APA, Harvard, Vancouver, ISO, and other styles

28

Lin, Brian K. "An unsupervised neural network fault discriminating system implementation for on-line condition monitoring and diagnostics of induction machines." Diss., Georgia Institute of Technology, 1998. http://hdl.handle.net/1853/14957.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Belharbi, Soufiane. "Neural networks regularization through representation learning." Thesis, Normandie, 2018. http://www.theses.fr/2018NORMIR10/document.

Full text

Abstract:

Les modèles de réseaux de neurones et en particulier les modèles profonds sont aujourd'hui l'un des modèles à l'état de l'art en apprentissage automatique et ses applications. Les réseaux de neurones profonds récents possèdent de nombreuses couches cachées ce qui augmente significativement le nombre total de paramètres. L'apprentissage de ce genre de modèles nécessite donc un grand nombre d'exemples étiquetés, qui ne sont pas toujours disponibles en pratique. Le sur-apprentissage est un des problèmes fondamentaux des réseaux de neurones, qui se produit lorsque le modèle apprend par coeur les données d'apprentissage, menant à des difficultés à généraliser sur de nouvelles données. Le problème du sur-apprentissage des réseaux de neurones est le thème principal abordé dans cette thèse. Dans la littérature, plusieurs solutions ont été proposées pour remédier à ce problème, tels que l'augmentation de données, l'arrêt prématuré de l'apprentissage ("early stopping"), ou encore des techniques plus spécifiques aux réseaux de neurones comme le "dropout" ou la "batch normalization". Dans cette thèse, nous abordons le sur-apprentissage des réseaux de neurones profonds sous l'angle de l'apprentissage de représentations, en considérant l'apprentissage avec peu de données. Pour aboutir à cet objectif, nous avons proposé trois différentes contributions. La première contribution, présentée dans le chapitre 2, concerne les problèmes à sorties structurées dans lesquels les variables de sortie sont à grande dimension et sont généralement liées par des relations structurelles. Notre proposition vise à exploiter ces relations structurelles en les apprenant de manière non-supervisée avec des autoencodeurs. Nous avons validé notre approche sur un problème de régression multiple appliquée à la détection de points d'intérêt dans des images de visages. Notre approche a montré une accélération de l'apprentissage des réseaux et une amélioration de leur généralisation. La deuxième contribution, présentée dans le chapitre 3, exploite la connaissance a priori sur les représentations à l'intérieur des couches cachées dans le cadre d'une tâche de classification. Cet à priori est basé sur la simple idée que les exemples d'une même classe doivent avoir la même représentation interne. Nous avons formalisé cet à priori sous la forme d'une pénalité que nous avons rajoutée à la fonction de perte. Des expérimentations empiriques sur la base MNIST et ses variantes ont montré des améliorations dans la généralisation des réseaux de neurones, particulièrement dans le cas où peu de données d'apprentissage sont utilisées. Notre troisième et dernière contribution, présentée dans le chapitre 4, montre l'intérêt du transfert d'apprentissage ("transfer learning") dans des applications dans lesquelles peu de données d'apprentissage sont disponibles. L'idée principale consiste à pré-apprendre les filtres d'un réseau à convolution sur une tâche source avec une grande base de données (ImageNet par exemple), pour les insérer par la suite dans un nouveau réseau sur la tâche cible. Dans le cadre d'une collaboration avec le centre de lutte contre le cancer "Henri Becquerel de Rouen", nous avons construit un système automatique basé sur ce type de transfert d'apprentissage pour une application médicale où l'on dispose d’un faible jeu de données étiquetées. Dans cette application, la tâche consiste à localiser la troisième vertèbre lombaire dans un examen de type scanner. L’utilisation du transfert d’apprentissage ainsi que de prétraitements et de post traitements adaptés a permis d’obtenir des bons résultats, autorisant la mise en oeuvre du modèle en routine clinique
Neural network models and deep models are one of the leading and state of the art models in machine learning. They have been applied in many different domains. Most successful deep neural models are the ones with many layers which highly increases their number of parameters. Training such models requires a large number of training samples which is not always available. One of the fundamental issues in neural networks is overfitting which is the issue tackled in this thesis. Such problem often occurs when the training of large models is performed using few training samples. Many approaches have been proposed to prevent the network from overfitting and improve its generalization performance such as data augmentation, early stopping, parameters sharing, unsupervised learning, dropout, batch normalization, etc. In this thesis, we tackle the neural network overfitting issue from a representation learning perspective by considering the situation where few training samples are available which is the case of many real world applications. We propose three contributions. The first one presented in chapter 2 is dedicated to dealing with structured output problems to perform multivariate regression when the output variable y contains structural dependencies between its components. Our proposal aims mainly at exploiting these dependencies by learning them in an unsupervised way. Validated on a facial landmark detection problem, learning the structure of the output data has shown to improve the network generalization and speedup its training. The second contribution described in chapter 3 deals with the classification task where we propose to exploit prior knowledge about the internal representation of the hidden layers in neural networks. This prior is based on the idea that samples within the same class should have the same internal representation. We formulate this prior as a penalty that we add to the training cost to be minimized. Empirical experiments over MNIST and its variants showed an improvement of the network generalization when using only few training samples. Our last contribution presented in chapter 4 showed the interest of transfer learning in applications where only few samples are available. The idea consists in re-using the filters of pre-trained convolutional networks that have been trained on large datasets such as ImageNet. Such pre-trained filters are plugged into a new convolutional network with new dense layers. Then, the whole network is trained over a new task. In this contribution, we provide an automatic system based on such learning scheme with an application to medical domain. In this application, the task consists in localizing the third lumbar vertebra in a 3D CT scan. A pre-processing of the 3D CT scan to obtain a 2D representation and a post-processing to refine the decision are included in the proposed system. This work has been done in collaboration with the clinic "Rouen Henri Becquerel Center" who provided us with data

APA, Harvard, Vancouver, ISO, and other styles

30

Yuan, Xiao. "Graph neural networks for spatial gene expression analysis of the developing human heart." Thesis, Uppsala universitet, Institutionen för biologisk grundutbildning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-427330.

Full text

Abstract:

Single-cell RNA sequencing and in situ sequencing were combined in a recent study of the developing human heart to explore the transcriptional landscape at three developmental stages. However, the method used in the study to create the spatial cellular maps has some limitations. It relies on image segmentation of the nuclei and cell types defined in advance by single-cell sequencing. In this study, we applied a new unsupervised approach based on graph neural networks on the in situ sequencing data of the human heart to find spatial gene expression patterns and detect novel cell and sub-cell types. In this thesis, we first introduce some relevant background knowledge about the sequencing techniques that generate our data, machine learning in single-cell analysis, and deep learning on graphs. We have explored several graph neural network models and algorithms to learn embeddings for spatial gene expression. Dimensionality reduction and cluster analysis were performed on the embeddings for visualization and identification of biologically functional domains. Based on the cluster gene expression profiles, locations of the clusters in the heart sections, and comparison with cell types defined in the previous study, the results of our experiments demonstrate that graph neural networks can learn meaningful representations of spatial gene expression in the human heart. We hope further validations of our clustering results could give new insights into cell development and differentiation processes of the human heart.

APA, Harvard, Vancouver, ISO, and other styles

31

Oquab, Maxime. "Convolutional neural networks : towards less supervision for visual recognition." Thesis, Paris Sciences et Lettres (ComUE), 2018. http://www.theses.fr/2018PSLEE061.

Full text

Abstract:

Les réseaux de neurones à convolution sont des algorithmes d’apprentissage flexibles qui tirent efficacement parti des importantes masses de données qui leur sont fournies pour l’entraînement. Malgré leur utilisation dans des applications industrielles dès les années 90, ces algorithmes n’ont pas été utilisés pour la reconnaissance d’image à cause de leurs faibles performances avec les images naturelles. C’est finalement grâce a l’apparition d’importantes quantités de données et de puissance de calcul que ces algorithmes ont pu révéler leur réel potentiel lors de la compétition ImageNet, menant à un changement de paradigme en reconnaissance d’image. La première contribution de cette thèse est une méthode de transfert d’apprentissage dans les réseaux à convolution pour la classification d’image. À l’aide d’une procédure de pré-entraînement, nous montrons que les représentations internes d’un réseau à convolution sont assez générales pour être utilisées sur d’autres tâches, et meilleures lorsque le pré-entraînement est réalisé avec plus de données. La deuxième contribution de cette thèse est un système faiblement supervisé pour la classification d’images, pouvant prédire la localisation des objets dans des scènes complexes, en utilisant, lors de l’entraînement, seulement l’indication de la présence ou l’absence des objets dans les images. La troisième contribution de cette thèse est une recherche de pistes de progression en apprentissage non-supervisé. Nous étudions l’algorithme récent des réseaux génératifs adversariaux et proposons l’utilisation d’un test statistique pour l’évaluation de ces modèles. Nous étudions ensuite les liens avec le problème de la causalité, et proposons un test statistique pour la découverte causale. Finalement, grâce a un lien établi récemment avec les problèmes de transport optimal, nous étudions ce que ces réseaux apprennent des données dans le cas non-supervisé
Convolutional Neural Networks are flexible learning algorithms for computer vision that scale particularly well with the amount of data that is provided for training them. Although these methods had successful applications already in the ’90s, they were not used in visual recognition pipelines because of their lesser performance on realistic natural images. It is only after the amount of data and the computational power both reached a critical point that these algorithms revealed their potential during the ImageNet challenge of 2012, leading to a paradigm shift in visual recogntion. The first contribution of this thesis is a transfer learning setup with a Convolutional Neural Network for image classification. Using a pre-training procedure, we show that image representations learned in a network generalize to other recognition tasks, and their performance scales up with the amount of data used in pre-training. The second contribution of this thesis is a weakly supervised setup for image classification that can predict the location of objects in complex cluttered scenes, based on a dataset indicating only with the presence or absence of objects in training images. The third contribution of this thesis aims at finding possible paths for progress in unsupervised learning with neural networks. We study the recent trend of Generative Adversarial Networks and propose two-sample tests for evaluating models. We investigate possible links with concepts related to causality, and propose a two-sample test method for the task of causal discovery. Finally, building on a recent connection with optimal transport, we investigate what these generative algorithms are learning from unlabeled data

APA, Harvard, Vancouver, ISO, and other styles

32

Candadai, Vasu Madhavun. "ANSWER : A Cognitively-Inspired System for the Unsupervised Detection of Semantically Salient Words in Texts." University of Cincinnati / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1439305439.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

McClintick, Kyle W. "Training Data Generation Framework For Machine-Learning Based Classifiers." Digital WPI, 2018. https://digitalcommons.wpi.edu/etd-theses/1276.

Full text

Abstract:

In this thesis, we propose a new framework for the generation of training data for machine learning techniques used for classification in communications applications. Machine learning-based signal classifiers do not generalize well when training data does not describe the underlying probability distribution of real signals. The simplest way to accomplish statistical similarity between training and testing data is to synthesize training data passed through a permutation of plausible forms of noise. To accomplish this, a framework is proposed that implements arbitrary channel conditions and baseband signals. A dataset generated using the framework is considered, and is shown to be appropriately sized by having $11\%$ lower entropy than state-of-the-art datasets. Furthermore, unsupervised domain adaptation can allow for powerful generalized training via deep feature transforms on unlabeled evaluation-time signals. A novel Deep Reconstruction-Classification Network (DRCN) application is introduced, which attempts to maintain near-peak signal classification accuracy despite dataset bias, or perturbations on testing data unforeseen in training. Together, feature transforms and diverse training data generated from the proposed framework, teaching a range of plausible noise, can train a deep neural net to classify signals well in many real-world scenarios despite unforeseen perturbations.

APA, Harvard, Vancouver, ISO, and other styles

34

Cherti, Mehdi. "Deep generative neural networks for novelty generation : a foundational framework, metrics and experiments." Thesis, Université Paris-Saclay (ComUE), 2018. http://www.theses.fr/2018SACLS029/document.

Full text

Abstract:

Des avancées significatives sur les réseaux de neurones profonds ont récemment permis le développement de technologies importantes comme les voitures autonomes et les assistants personnels intelligents basés sur la commande vocale. La plupart des succès en apprentissage profond concernent la prédiction, alors que les percées initiales viennent des modèles génératifs. Actuellement, même s'il existe des outils puissants dans la littérature des modèles génératifs basés sur les réseaux profonds, ces techniques sont essentiellement utilisées pour la prédiction ou pour générer des objets connus (i.e., des images de haute qualité qui appartiennent à des classes connues) : un objet généré qui est à priori inconnu est considéré comme une erreur (Salimans et al., 2016) ou comme un objet fallacieux (Bengio et al., 2013b). En d'autres termes, quand la prédiction est considérée comme le seul objectif possible, la nouveauté est vue comme une erreur - que les chercheurs ont essayé d'éliminer au maximum. Cette thèse défends le point de vue que, plutôt que d'éliminer ces nouveautés, on devrait les étudier et étudier le potentiel génératif des réseaux neuronaux pour créer de la nouveauté utile - particulièrement sachant l'importance économique et sociétale de la création d'objets nouveaux dans les sociétés contemporaines. Cette thèse a pour objectif d'étudier la génération de la nouveauté et sa relation avec les modèles de connaissance produits par les réseaux neurones profonds génératifs. Notre première contribution est la démonstration de l'importance des représentations et leur impact sur le type de nouveautés qui peuvent être générées : une conséquence clé est qu'un agent créatif a besoin de re-représenter les objets connus et utiliser cette représentation pour générer des objets nouveaux. Ensuite, on démontre que les fonctions objectives traditionnelles utilisées dans la théorie de l'apprentissage statistique, comme le maximum de vraisemblance, ne sont pas nécessairement les plus adaptées pour étudier la génération de nouveauté. On propose plusieurs alternatives à un niveau conceptuel. Un deuxième résultat clé est la confirmation que les modèles actuels - qui utilisent les fonctions objectives traditionnelles - peuvent en effet générer des objets inconnus. Cela montre que même si les fonctions objectives comme le maximum de vraisemblance s'efforcent à éliminer la nouveauté, les implémentations en pratique échouent à le faire. A travers une série d'expérimentations, on étudie le comportement de ces modèles ainsi que les objets qu'ils génèrent. En particulier, on propose une nouvelle tâche et des métriques pour la sélection de bons modèles génératifs pour la génération de la nouveauté. Finalement, la thèse conclue avec une série d'expérimentations qui clarifie les caractéristiques des modèles qui génèrent de la nouveauté. Les expériences montrent que la sparsité, le niveaux du niveau de corruption et la restriction de la capacité des modèles tuent la nouveauté et que les modèles qui arrivent à reconnaître des objets nouveaux arrivent généralement aussi à générer de la nouveauté
In recent years, significant advances made in deep neural networks enabled the creation of groundbreaking technologies such as self-driving cars and voice-enabled personal assistants. Almost all successes of deep neural networks are about prediction, whereas the initial breakthroughs came from generative models. Today, although we have very powerful deep generative modeling techniques, these techniques are essentially being used for prediction or for generating known objects (i.e., good quality images of known classes): any generated object that is a priori unknown is considered as a failure mode (Salimans et al., 2016) or as spurious (Bengio et al., 2013b). In other words, when prediction seems to be the only possible objective, novelty is seen as an error that researchers have been trying hard to eliminate. This thesis defends the point of view that, instead of trying to eliminate these novelties, we should study them and the generative potential of deep nets to create useful novelty, especially given the economic and societal importance of creating new objects in contemporary societies. The thesis sets out to study novelty generation in relationship with data-driven knowledge models produced by deep generative neural networks. Our first key contribution is the clarification of the importance of representations and their impact on the kind of novelties that can be generated: a key consequence is that a creative agent might need to rerepresent known objects to access various kinds of novelty. We then demonstrate that traditional objective functions of statistical learning theory, such as maximum likelihood, are not necessarily the best theoretical framework for studying novelty generation. We propose several other alternatives at the conceptual level. A second key result is the confirmation that current models, with traditional objective functions, can indeed generate unknown objects. This also shows that even though objectives like maximum likelihood are designed to eliminate novelty, practical implementations do generate novelty. Through a series of experiments, we study the behavior of these models and the novelty they generate. In particular, we propose a new task setup and metrics for selecting good generative models. Finally, the thesis concludes with a series of experiments clarifying the characteristics of models that can exhibit novelty. Experiments show that sparsity, noise level, and restricting the capacity of the net eliminates novelty and that models that are better at recognizing novelty are also good at generating novelty

APA, Harvard, Vancouver, ISO, and other styles

35

Parkinson, Jon. "Representation learning with a temporally coherent mixed-representation." Thesis, University of Manchester, 2017. https://www.research.manchester.ac.uk/portal/en/theses/representation-learning-with-a-temporally-coherent-mixedrepresentation(ba48bd9e-80ed-4d37-b743-cb149bc498ee).html.

Full text

Abstract:

Guiding a representation towards capturing temporally coherent aspects present invideo improves object identity encoding. Existing models apply temporal coherenceuniformly over all features based on the assumption that optimal encoding of objectidentity only requires temporally stable components. We test the validity of this assumptionby exploring the effects of applying a mixture of temporally coherent invariantfeatures, alongside variable features, in a single 'mixed' representation. Applyingtemporal coherence to different proportions of the available features, we evaluate arange of models on a supervised object classification task. This series of experimentswas tested on three video datasets, each with a different complexity of object shape andmotion. We also investigated whether a mixed-representation improves the capture ofinformation components associated with object position, alongside object identity, ina single representation. Tests were initially applied using a single layer autoencoderas a test bed, followed by subsequent tests investigating whether similar behaviouroccurred in the more abstract features learned by a deep network. A representationapplying temporal coherence in some fashion produced the best results in all tests,on both single layered and deep networks. The majority of tests favoured a mixed representation,especially in cases where the quantity of labelled data available to thesupervised task was plentiful. This work is the first time a mixed-representation hasbeen investigated, and demonstrates its use as a method for representation learning.

APA, Harvard, Vancouver, ISO, and other styles

36

Mathur, Nitin O. "Application of Autoencoder Ensembles in Anomaly and Intrusion Detection using Time-Based Analysis." University of Cincinnati / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ucin161374876195402.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Li, Yingzhen. "Approximate inference : new visions." Thesis, University of Cambridge, 2018. https://www.repository.cam.ac.uk/handle/1810/277549.

Full text

Abstract:

Nowadays machine learning (especially deep learning) techniques are being incorporated to many intelligent systems affecting the quality of human life. The ultimate purpose of these systems is to perform automated decision making, and in order to achieve this, predictive systems need to return estimates of their confidence. Powered by the rules of probability, Bayesian inference is the gold standard method to perform coherent reasoning under uncertainty. It is generally believed that intelligent systems following the Bayesian approach can better incorporate uncertainty information for reliable decision making, and be less vulnerable to attacks such as data poisoning. Critically, the success of Bayesian methods in practice, including the recent resurgence of Bayesian deep learning, relies on fast and accurate approximate Bayesian inference applied to probabilistic models. These approximate inference methods perform (approximate) Bayesian reasoning at a relatively low cost in terms of time and memory, thus allowing the principles of Bayesian modelling to be applied to many practical settings. However, more work needs to be done to scale approximate Bayesian inference methods to big systems such as deep neural networks and large-scale dataset such as ImageNet. In this thesis we develop new algorithms towards addressing the open challenges in approximate inference. In the first part of the thesis we develop two new approximate inference algorithms, by drawing inspiration from the well known expectation propagation and message passing algorithms. Both approaches provide a unifying view of existing variational methods from different algorithmic perspectives. We also demonstrate that they lead to better calibrated inference results for complex models such as neural network classifiers and deep generative models, and scale to large datasets containing hundreds of thousands of data-points. In the second theme of the thesis we propose a new research direction for approximate inference: developing algorithms for fitting posterior approximations of arbitrary form, by rethinking the fundamental principles of Bayesian computation and the necessity of algorithmic constraints in traditional inference schemes. We specify four algorithmic options for the development of such new generation approximate inference methods, with one of them further investigated and applied to Bayesian deep learning tasks.

APA, Harvard, Vancouver, ISO, and other styles

38

Hassan, K. J. "Application of artificial neural networks for understanding and diagnosing the state of mastitis in dairy cattle." Lincoln University, 2007. http://hdl.handle.net/10182/633.

Full text

Abstract:

Bovine mastitis adversely affects the dairy industry around the world. This disease is caused by a diverse range of bacteria, broadly categorised as minor and major pathogens. In-line tools that help identify these bacterial groupings in the early stages of the disease are advantageous as timely decisions could be made before the cow develops any clinical symptoms. The first objective of this research was to identify the most informative milk parameters for the detection of minor and major bacterial pathogens. The second objective of this research was to evaluate the potential of supervised and unsupervised neural network learning paradigms for the detection of minor infected and major infected quarters in the early stages of the disease. The third objective was to evaluate the effects of different proportions of infected to non-infected cases in the training data set on the correct classification rate of the supervised neural network models as there are proportionately more non-infected cases in a herd than infected cases. A database developed at Lincoln University was used to achieve the research objectives. Starting at calving, quarter milk samples were collected weekly from 112 cows for a period of fourteen weeks, resulting in 4852 samples with complete records for somatic cell count (SCC), electrical resistance, protein percentage, fat percentage, and bacteriological status. To account for the effects of the stage of lactation on milk parameters with respect to days in milking, data was divided into three days in milk ranges. In addition, cow variation was accounted for by the sire family from which the cow originated and the lactation number of each cow. Data was pre-processed before the application of advanced analytical techniques. Somatic cell score (SCS) and electrical resistance index were derived from somatic cell count and electrical resistance, respectively. After pre-processing, the data was divided into training and validation sets for the unsupervised neural network modelling experiment and, for the supervised neural network modelling experiments, the data was divided into training, calibration and validation sets. Prior to any modelling experiments, the data was analysed using statistical and multivariate visualisation techniques. Correlations (p<0.05) were found between the infection status of a quarter and its somatic cell score (SCS, 0.86), electrical resistance index (ERI, -0.59) and protein percentage (PP, 0.33). The multivariate parallel visualisation analysis validated the correlation analysis. Due to significant multicolinearity [Correlations: SCS and ERI (-0.65: p<0.05); SCS and PP (0.32: p<0.05); ERI and PP (-0.35: p<0.05)], the original variables were decorrelated using principle component analysis. SCS and ERI were found to be the most informative variables for discriminating between non-infected, minor infected and major infected cases. Unsupervised neural network (USNN) model was trained using the training data set which was extracted from the database, containing approximately equal number of randomly selected records for each bacteriological status [not infected (NI), infected with a major pathogen (MJI) and infected with a minor pathogen (MNI)]. The USNN model was validated with the remaining data using the four principle components, days in milk (DIM), lactation number (LN), sire number, and bacteriological status (BS). The specificity of the USNN model in correctly identifying non infected cases was 97%. Sensitivities for correctly detecting minor and major infections were 89% and 80%, respectively. The supervised neural network (SNN) models were trained, calibrated and validated with several sets of training, calibration and validation data, which were randomly extracted from the database in such a way that each set has a different proportion of infected to non-infected cases ranging from 1:1 to 1:10. The overall accuracy of these models based on validation data sets gradually increased with increase in the number of non-infected cases in the data sets (80% for the 1:1, 84% for 1:2, 86% for 1:4 and 93% for 1:10). Specificities of the best models for correctly recognising non-infected cases for the four data sets were 82% for 1:1, 91% for 1:2, 94% for 1:4 and 98% for 1:10. Sensitivities for correctly recognising minor infected cases for the four data sets were 86% for 1:1, 76% for 1:2, 71% for 1:4 and 44% for 1:10. Sensitivities for correctly recognising major infected cases for the four data sets were 20% for 1:1, 20% for 1:2, 30% for 1:4 and 40% for 1:10. Overall, sensitivity for the minor infected cases decreased while that of major infected cases increased with increase in the number non-infected cases in the training data set. Due to the very low prevalence of MJI category in this particular herd, results for this category may be inconclusive. This research suggests that somatic cell score and electrical resistance index of milk were the most effective variables for detecting the infection status of a quarter followed by milk protein and fat percentage. The neural network models were able to differentiate milk containing minor and major bacterial pathogens based on milk parameters associated with mastitis. It is concluded that the neural network models can be developed and incorporated into milking machines to provide an efficient and effective method for the diagnosis of mastitis.

APA, Harvard, Vancouver, ISO, and other styles

39

Simões, Alexandre da Silva. "Aprendizado não-supervisionado em redes neurais pulsadas de base radial." Universidade de São Paulo, 2006. http://www.teses.usp.br/teses/disponiveis/3/3141/tde-15092006-153353/.

Full text

Abstract:

Redes neurais pulsadas - redes que utilizam uma codificação temporal da informação - têm despontado como uma nova e promissora abordagem dentro do paradigma conexionista emergente da ciência cognitiva. Um desses novos modelos é a rede neural pulsada de base radial, capaz de armazenar informação nos tempos de atraso axonais dos neurônios e que comporta algoritmos explícitos de treinamento. A recente proposição de uma sistemática para a codificação temporal dos dados de entrada utilizando campos receptivos gaussianos tem apresentado interessantes resultados na tarefa do agrupamento de dados (clustering). Este trabalho propõe uma função para o aprendizado não supervisionado dessa rede, com o objetivo de simplificar a sistemática de calibração de alguns dos seus parâmetros-chave, aprimorando a convergência da rede neural pulsada no aprendizado baseado em instâncias. O desempenho desse modelo é avaliado na tarefa de classificação de padrões, particularmente na classificação de pixels em imagens coloridas no domínio da visão computacional.
Pulsed neural networks - networks that encode information in the timing of spikes - have been studied as a new and promising approach in the artificial neural networks paradigm, emergent from cognitive science. One of these new models is the pulsed neural network with radial basis function, a network able to store information in the axonal propagation delay of neurons. Recently, a new method for encoding input-data by population code using gaussian receptive fields has showed interesting results in the clustering task. The present work proposes a function for the unsupervised learning task in this network, which goal includes the simplification of the calibration of the network key parameters and the enhancement of the pulsed neural network convergence to instance based learning. The performance of this model is evaluated for pattern classification, particularly for the pixel colors classification task, in the computer vision domain.

APA, Harvard, Vancouver, ISO, and other styles

40

Dekhtiar, Jonathan. "Deep Learning and unsupervised learning to automate visual inspection in the manufacturing industry." Thesis, Compiègne, 2019. http://www.theses.fr/2019COMP2513.

Full text

Abstract:

La croissance exponentielle des besoins et moyens informatiques implique un besoin croissant d’automatisation des procédés industriels. Ce constat est en particulier visible pour l’inspection visuelle automatique sur ligne de production. Bien qu’étudiée depuis 1970, peine toujours à être appliquée à de larges échelles et à faible coûts. Les méthodes employées dépendent grandement de la disponibilité des experts métiers. Ce qui provoque inévitablement une augmentation des coûts et une réduction de la flexibilité des méthodes employées. Depuis 2012, les avancées dans le domaine associé à l’étude des réseaux neuronaux profonds (i.e. Deep Learning) a permis de nombreux progrès en ce sens, notamment grâce au réseaux neuronaux convolutif qui ont atteint des performances proches de l’humain dans de nombreux domaines associées à la perception visuelle (e.g. reconnaissance et détection d’objets, etc.). Cette thèse propose une approche non supervisée pour répondre aux besoins de l’inspection visuelle automatique. Cette méthode, baptisé AnoAEGAN, combine l’apprentissage adversaire et l’estimation d’une fonction de densité de probabilité. Ces deux approches complémentaires permettent d’estimer jointement la probabilité pixel par pixel d’un défaut visuel sur une image. Le modèle est entrainé à partir d’un nombre très limités d’images (i.e. inférieur à 1000 images) sans utilisation de connaissance expert pour « étiqueter » préalablement les données. Cette méthode permet une flexibilité accrue par la rapidité d’entrainement du modèle et une grande versatilité, démontrée sur dix tâches différentes sans la moindre modification du modèle. Cette méthode devrait permettre de réduire les coûts de développement et le temps nécessaire de déploiement en production. Cette méthode peut être également déployée de manière complémentaire à une approche supervisée afin de bénéficier des avantages de chaque approche
Although studied since 1970, automatic visual inspection on production lines still struggles to be applied on a large scale and at low cost. The methods used depend greatly on the availability of domain experts. This inevitably leads to increased costs and reduced flexibility in the methods used. Since 2012, advances in the field of Deep Learning have enabled many advances in this direction, particularly thanks to convolutional neura networks that have achieved near-human performance in many areas associated with visual perception (e.g. object recognition and detection, etc.). This thesis proposes an unsupervised approach to meet the needs of automatic visual inspection. This method, called AnoAEGAN, combines adversarial learning and the estimation of a probability density function. These two complementary approaches make it possible to jointly estimate the pixel-by-pixel probability of a visual defect on an image. The model is trained from a very limited number of images (i.e. less than 1000 images) without using expert knowledge to "label" the data beforehand. This method allows increased flexibility with a limited training time and therefore great versatility, demonstrated on ten different tasks without any modification of the model. This method should reduce development costs and the time required to deploy in production. This method can also be deployed in a complementary way to a supervised approach in order to benefit from the advantages of each approach

APA, Harvard, Vancouver, ISO, and other styles

41

Choi, Jin-Woo. "Action Recognition with Knowledge Transfer." Diss., Virginia Tech, 2021. http://hdl.handle.net/10919/101780.

Full text

Abstract:

Recent progress on deep neural networks has shown remarkable action recognition performance from videos. The remarkable performance is often achieved by transfer learning: training a model on a large-scale labeled dataset (source) and then fine-tuning the model on the small-scale labeled datasets (targets). However, existing action recognition models do not always generalize well on new tasks or datasets because of the following two reasons. i) Current action recognition datasets have a spurious correlation between action types and background scene types. The models trained on these datasets are biased towards the scene instead of focusing on the actual action. This scene bias leads to poor generalization performance. ii) Directly testing the model trained on the source data on the target data leads to poor performance as the source, and target distributions are different. Fine-tuning the model on the target data can mitigate this issue. However, manual labeling small- scale target videos is labor-intensive. In this dissertation, I propose solutions to these two problems. For the first problem, I propose to learn scene-invariant action representations to mitigate the scene bias in action recognition models. Specifically, I augment the standard cross-entropy loss for action classification with 1) an adversarial loss for the scene types and 2) a human mask confusion loss for videos where the human actors are invisible. These two losses encourage learning representations unsuitable for predicting 1) the correct scene types and 2) the correct action types when there is no evidence. I validate the efficacy of the proposed method by transfer learning experiments. I trans- fer the pre-trained model to three different tasks, including action classification, temporal action localization, and spatio-temporal action detection. The results show consistent improvement over the baselines for every task and dataset. I formulate human action recognition as an unsupervised domain adaptation (UDA) problem to handle the second problem. In the UDA setting, we have many labeled videos as source data and unlabeled videos as target data. We can use already exist- ing labeled video datasets as source data in this setting. The task is to align the source and target feature distributions so that the learned model can generalize well on the target data. I propose 1) aligning the more important temporal part of each video and 2) encouraging the model to focus on action, not the background scene, to learn domain-invariant action representations. The proposed method is simple and intuitive while achieving state-of-the-art performance without training on a lot of labeled target videos. I relax the unsupervised target data setting to a sparsely labeled target data setting. Then I explore the semi-supervised video action recognition, where we have a lot of labeled videos as source data and sparsely labeled videos as target data. The semi-supervised setting is practical as sometimes we can afford a little bit of cost for labeling target data. I propose multiple video data augmentation methods to inject photometric, geometric, temporal, and scene invariances to the action recognition model in this setting. The resulting method shows favorable performance on the public benchmarks.
Doctor of Philosophy
Recent progress on deep learning has shown remarkable action recognition performance. The remarkable performance is often achieved by transferring the knowledge learned from existing large-scale data to the small-scale data specific to applications. However, existing action recog- nition models do not always work well on new tasks and datasets because of the following two problems. i) Current action recognition datasets have a spurious correlation between action types and background scene types. The models trained on these datasets are biased towards the scene instead of focusing on the actual action. This scene bias leads to poor performance on the new datasets and tasks. ii) Directly testing the model trained on the source data on the target data leads to poor performance as the source, and target distributions are different. Fine-tuning the model on the target data can mitigate this issue. However, manual labeling small-scale target videos is labor-intensive. In this dissertation, I propose solutions to these two problems. To tackle the first problem, I propose to learn scene-invariant action representations to mitigate background scene- biased human action recognition models for the first problem. Specifically, the proposed method learns representations that cannot predict the scene types and the correct actions when there is no evidence. I validate the proposed method's effectiveness by transferring the pre-trained model to multiple action understanding tasks. The results show consistent improvement over the baselines for every task and dataset. To handle the second problem, I formulate human action recognition as an unsupervised learning problem on the target data. In this setting, we have many labeled videos as source data and unlabeled videos as target data. We can use already existing labeled video datasets as source data in this setting. The task is to align the source and target feature distributions so that the learned model can generalize well on the target data. I propose 1) aligning the more important temporal part of each video and 2) encouraging the model to focus on action, not the background scene. The proposed method is simple and intuitive while achieving state-of-the-art performance without training on a lot of labeled target videos. I relax the unsupervised target data setting to a sparsely labeled target data setting. Here, we have many labeled videos as source data and sparsely labeled videos as target data. The setting is practical as sometimes we can afford a little bit of cost for labeling target data. I propose multiple video data augmentation methods to inject color, spatial, temporal, and scene invariances to the action recognition model in this setting. The resulting method shows favorable performance on the public benchmarks.

APA, Harvard, Vancouver, ISO, and other styles

42

cruz, Magnus Alencar da. "AvaliaÃÃo de redes neurais competitivas em tarefas de quantizaÃÃo vetorial:um estudo comparativo." Universidade Federal do CearÃ, 2007. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=2016.

Full text

Abstract:

nÃo hÃ
Esta dissertaÃÃo tem como principal meta realizar um estudo comparativo do desempenho de algoritmos de redes neurais competitivas nÃo-supervisionadas em problemas de quantizaÃÃo vetorial (QV) e aplicaÃÃes correlatas, tais como anÃlise de agrupamentos (clustering) e compressÃo de imagens. A motivaÃÃo para tanto parte da percepÃÃo de que hÃ uma relativa escassez de estudos comparativos sistemÃticos entre algoritmos neurais e nÃo-neurais de anÃlise de agrupamentos na literatura especializada. Um total de sete algoritmos sÃo avaliados, a saber: algoritmo K -mÃdias e as redes WTA, FSCL, SOM, Neural-Gas, FuzzyCL e RPCL. De particular interesse Ã a seleÃÃo do nÃmero Ãtimo de neurÃnios. NÃo hÃ um mÃtodo que funcione para todas as situaÃÃes, restando portanto avaliar a influÃncia que cada tipo de mÃtrica exerce sobre algoritmo em estudo. Por exemplo, os algoritmos de QV supracitados sÃo bastante usados em tarefas de clustering. Neste tipo de aplicaÃÃo, a validaÃÃo dos agrupamentos Ã feita com base em Ãndices que quantificam os graus de compacidade e separabilidade dos agrupamentos encontrados, tais como Ãndice Dunn e Ãndice Davies-Bouldin (DB). JÃ em tarefas de compressÃo de imagens, determinado algoritmo de QV Ã avaliado em funÃÃo da qualidade da informaÃÃo reconstruÃda, daÃ as mÃtricas mais usadas serem o erro quadrÃtico mÃdio de quantizaÃÃo (EQMQ) ou a relaÃÃo sinal-ruÃdo de pico (PSNR). Empiricamente verificou-se que, enquanto o Ãndice DB favorece arquiteturas com poucos protÃtipos e o Dunn com muitos, as mÃtricas EQMQ e PSNR sempre favorecem nÃmeros ainda maiores. Nenhuma das mÃtricas supracitadas leva em consideraÃÃo o nÃmero de parÃmetros do modelo. Em funÃÃo disso, esta dissertaÃÃo propÃe o uso do critÃrio de informaÃÃo de Akaike (AIC) e o critÃrio do comprimento descritivo mÃnimo (MDL) de Rissanen para selecionar o nÃmero Ãtimo de protÃtipos. Este tipo de mÃtrica mostra-se Ãtil na busca do nÃmero de protÃtipos que satisfaÃa simultaneamente critÃrios opostos, ou seja, critÃrios que buscam o menor erro de reconstruÃÃo a todo custo (MSE e PSNR) e critÃrios que buscam clusters mais compactos e coesos (Ãndices Dunn e DB). Como conseqÃÃncia, o nÃmero de protÃtipos obtidos pelas mÃtricas AIC e MDL Ã geralmente um valor intermediÃrio, i.e. nem tÃo baixo quanto o sugerido pelos Ãndices Dunn e DB, nem tÃo altos quanto o sugerido pelas mÃtricas MSE e PSNR. Outra conclusÃo importante Ã que nÃo necessariamente os algoritmos mais sofisticados do ponto de vista da modelagem, tais como as redes SOM e Neural-Gas, sÃo os que apresentam melhores desempenhos em tarefas de clustering e quantizaÃÃo vetorial. Os algoritmos FSCL e FuzzyCL sÃo os que apresentam melhores resultados em tarefas de quantizaÃÃo vetorial, com a rede FSCL apresentando melhor relaÃÃo custo-benefÃcio, em funÃÃo do seu menor custo computacional. Para finalizar, vale ressaltar que qualquer que seja o algoritmo escolhido, se o mesmo tiver seus parÃmetros devidamente ajustados e seus desempenhos devidamente avaliados, as diferenÃas de performance entre os mesmos sÃo desprezÃveis, ficando como critÃrio de desempate o custo computacional.
The main goal of this master thesis was to carry out a comparative study of the performance of algorithms of unsupervised competitive neural networks in problems of vector quantization (VQ) tasks and related applications, such as cluster analysis and image compression. This study is mainly motivated by the relative scarcity of systematic comparisons between neural and nonneural algorithms for VQ in specialized literature. A total of seven algorithms are evaluated, namely: K-means, WTA, FSCL, SOM, Neural-Gas, FuzzyCL and RPCL. Of particular interest is the problem of selecting an adequate number of neurons given a particular vector quantization problem. Since there is no widespread method that works satisfactorily for all applications, the remaining alternative is to evaluate the influence that each type of evaluation metric has on a specific algorithm. For example, the aforementioned vector quantization algorithms are widely used in clustering-related tasks. For this type of application, cluster validation is based on indexes that quantify the degrees of compactness and separability among clusters, such as the Dunn Index and the Davies- Bouldin (DB) Index. In image compression tasks, however, a given vector quantization algorithm is evaluated in terms of the quality of the reconstructed information, so that the most used evaluation metrics are the mean squared quantization error (MSQE) and the peak signal-to-noise ratio (PSNR). This work verifies empirically that, while the indices Dunn and DB or favors architectures with many prototypes (Dunn) or with few prototypes (DB), metrics MSE and PSNR always favor architectures with well bigger amounts. None of the evaluation metrics cited previously takes into account the number of parameters of the model. Thus, this thesis evaluates the feasibility of the use of the Akaikeâs information criterion (AIC) and Rissanenâs minimum description length (MDL) criterion to select the optimal number of prototypes. This type of evaluation metric indeed reveals itself useful in the search of the number of prototypes that simultaneously satisfies conflicting criteria, i.e. those favoring more compact and cohesive clusters (Dunn and DB indices) versus those searching for very low reconstruction errors (MSE and PSNR). Thus, the number of prototypes suggested by AIC and MDL is generally an intermediate value, i.e nor so low as much suggested for the indexes Dunn and DB, nor so high as much suggested one for metric MSE and PSNR. Another important conclusion is that sophisticated models, such as the SOM and Neural- Gas networks, not necessarily have the best performances in clustering and VQ tasks. For example, the algorithms FSCL and FuzzyCL present better results in terms of the the of the reconstructed information, with the FSCL presenting better cost-benefit ratio due to its lower computational cost. As a final remark, it is worth emphasizing that if a given algorithm has its parameters suitably tuned and its performance fairly evaluated, the differences in performance compared to others prototype-based algorithms is minimum, with the coputational cost being used to break ties.

APA, Harvard, Vancouver, ISO, and other styles

43

Cherif, Aymen. "Réseaux de neurones, SVM et approches locales pour la prévision de séries temporelles." Thesis, Tours, 2013. http://www.theses.fr/2013TOUR4003/document.

Full text

Abstract:

La prévision des séries temporelles est un problème qui est traité depuis de nombreuses années. On y trouve des applications dans différents domaines tels que : la finance, la médecine, le transport, etc. Dans cette thèse, on s’est intéressé aux méthodes issues de l’apprentissage artificiel : les réseaux de neurones et les SVM. On s’est également intéressé à l’intérêt des méta-méthodes pour améliorer les performances des prédicteurs, notamment l’approche locale. Dans une optique de diviser pour régner, les approches locales effectuent le clustering des données avant d’affecter les prédicteurs aux sous ensembles obtenus. Nous présentons une modification dans l’algorithme d’apprentissage des réseaux de neurones récurrents afin de les adapter à cette approche. Nous proposons également deux nouvelles techniques de clustering, la première basée sur les cartes de Kohonen et la seconde sur les arbres binaires
Time series forecasting is a widely discussed issue for many years. Researchers from various disciplines have addressed it in several application areas : finance, medical, transportation, etc. In this thesis, we focused on machine learning methods : neural networks and SVM. We have also been interested in the meta-methods to push up the predictor performances, and more specifically the local models. In a divide and conquer strategy, the local models perform a clustering over the data sets before different predictors are affected into each obtained subset. We present in this thesis a new algorithm for recurrent neural networks to use them as local predictors. We also propose two novel clustering techniques suitable for local models. The first is based on Kohonen maps, and the second is based on binary trees

APA, Harvard, Vancouver, ISO, and other styles

44

Stella, Federico. "Learning a Local Reference Frame for Point Clouds using Spherical CNNs." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20197/.

Full text

Abstract:

Uno dei problemi più importanti della 3D Computer Vision è il cosiddetto surface matching, che consiste nel trovare corrispondenze tra oggetti tridimensionali. Attualmente il problema viene affrontato calcolando delle feature locali e compatte, chiamate descrittori, che devono essere riconosciute e messe in corrispondenza al mutare della posa dell'oggetto nello spazio, e devono quindi essere invarianti rispetto all'orientazione. Il metodo più usato per ottenere questa proprietà consiste nell'utilizzare dei Local Reference Frame (LRF): sistemi di coordinate locali che forniscono un'orientazione canonica alle porzioni di oggetti 3D che vengono usate per calcolare i descrittori. In letteratura esistono diversi modi per calcolare gli LRF, ma fanno tutti uso di algoritmi progettati manualmente. Vi è anche una recente proposta che utilizza reti neurali, tuttavia queste vengono addestrate mediante feature specificamente progettate per lo scopo, il che non permette di sfruttare pienamente i benefici delle moderne strategie di end-to-end learning. Lo scopo di questo lavoro è utilizzare un approccio data-driven per far imparare a una rete neurale il calcolo di un Local Reference Frame a partire da point cloud grezze, producendo quindi il primo esempio di end-to-end learning applicato alla stima di LRF. Per farlo, sfruttiamo una recente innovazione chiamata Spherical Convolutional Neural Networks, le quali generano e processano segnali nello spazio SO(3) e sono quindi naturalmente adatte a rappresentare e stimare orientazioni e LRF. Confrontiamo le prestazioni ottenute con quelle di metodi esistenti su benchmark standard, ottenendo risultati promettenti.

APA, Harvard, Vancouver, ISO, and other styles

45

Navarro, Marco Vin?cius Monteiro. "Emprego de redes neurais artificiais supervisionadas e n?o supervisionadas no estudo de par?metros reol?gicos de excipientes farmac?uticos s?lidos." Universidade Federal do Rio Grande do Norte, 2014. http://repositorio.ufrn.br:8080/jspui/handle/123456789/13866.

Full text

Abstract:

Made available in DSpace on 2014-12-17T14:25:22Z (GMT). No. of bitstreams: 1 MarcoVMN_TESE.pdf: 3982733 bytes, checksum: 381ae79721c75a30e3373fe4487512c7 (MD5) Previous issue date: 2014-02-05
In this paper artificial neural network (ANN) based on supervised and unsupervised algorithms were investigated for use in the study of rheological parameters of solid pharmaceutical excipients, in order to develop computational tools for manufacturing solid dosage forms. Among four supervised neural networks investigated, the best learning performance was achieved by a feedfoward multilayer perceptron whose architectures was composed by eight neurons in the input layer, sixteen neurons in the hidden layer and one neuron in the output layer. Learning and predictive performance relative to repose angle was poor while to Carr index and Hausner ratio (CI and HR, respectively) showed very good fitting capacity and learning, therefore HR and CI were considered suitable descriptors for the next stage of development of supervised ANNs. Clustering capacity was evaluated for five unsupervised strategies. Network based on purely unsupervised competitive strategies, classic "Winner-Take-All", "Frequency-Sensitive Competitive Learning" and "Rival-Penalize Competitive Learning" (WTA, FSCL and RPCL, respectively) were able to perform clustering from database, however this classification was very poor, showing severe classification errors by grouping data with conflicting properties into the same cluster or even the same neuron. On the other hand it could not be established what was the criteria adopted by the neural network for those clustering. Self-Organizing Maps (SOM) and Neural Gas (NG) networks showed better clustering capacity. Both have recognized the two major groupings of data corresponding to lactose (LAC) and cellulose (CEL). However, SOM showed some errors in classify data from minority excipients, magnesium stearate (EMG) , talc (TLC) and attapulgite (ATP). NG network in turn performed a very consistent classification of data and solve the misclassification of SOM, being the most appropriate network for classifying data of the study. The use of NG network in pharmaceutical technology was still unpublished. NG therefore has great potential for use in the development of software for use in automated classification systems of pharmaceutical powders and as a new tool for mining and clustering data in drug development
Neste trabalho foram estudadas redes neurais artificiais (RNAs) baseadas em algoritmos supervisionados e n?o supervisionados para emprego no estudo de par?metros reol?gicos de excipientes farmac?uticos s?lidos, visando desenvolver ferramentas computacionais para o desenvolvimento de formas farmac?uticas s?lidas. Foram estudadas quatro redes neurais artificiais supervisionadas e cinco n?o supervisionadas. Todas as RNAs supervisionadas foram baseadas em arquitetura de rede perceptron multicamada alimentada ? frente (feedfoward MLP). Das cinco RNAs n?o supervisionadas, tr?s foram baseadas em estrat?gias puramente competitivas, "Winner-Take- All" cl?ssica, "Frequency-Sensitive Competitive Learning" e "Rival-Penalize Competitive Learning" (WTA, FSCL e RPCL, respectivamente). As outras duas redes n?o supervisionadas, Self- Organizing Map e Neural Gas (SOM e NG) foram baseadas estrat?gias competitivo-cooperativas. O emprego da rede NG em tecnologia farmac?utica ? ainda in?dito e pretende-se avaliar seu potencial de emprego como nova ferramenta de minera??o e classifica??o de dados no desenvolvimento de medicamentos. Entre os prot?tipos de RNAs supervisionadas o melhor desempenho foi conseguido com uma rede de arquitetura composta por 8 neur?nios de entrada, 16 neur?nios escondidos e 1 neur?nio de sa?da. O aprendizado de rede e a capacidade preditiva em rela??o ao ?ngulo de repouso (α) foi deficiente, e muito boa para o ?ndice de Carr e fator de Hausner (IC, FH). Por esse motivo IC e FH foram considerados bons descritores para uma pr?xima etapa de desenvolvimento das RNAs supervisionadas. As redes, WTA, RPCL e FSCL, foram capazes de estabelecer agrupamentos dentro da massa de dados, por?m apresentaram erros grosseiros de classifica??o caracterizados pelo agrupamento de dados com propriedades conflitantes, e tamb?m n?o foi poss?vel estabelecer qual o crit?rio de classifica??o adotado. Tais resultados demonstraram a inviabilidade pr?tica dessas redes para os sistemas estudados sob nossas condi??es experimentais. As redes SOM e NG mostraram uma capacidade de classifica??o muito superior ?s RNAs puramente competitivas. Ambas as redes reconheceram os dois agrupamentos principais de dados correspondentes ? lactose (LAC) e celulose (CEL). Entretanto a rede som demonstrou defici?ncia na classifica??o de dados relativos aos excipientes minorit?rios, estearato de magn?sio (EMG), talco (TLC) e atapulgita (ATP). A rede NG, por sua vez, estabeleceu uma classifica??o muito consistente dos dados e resolveu o erro de classifica??o apresentados pela rede SOM, mostrando-se a rede mais adequada para a classifica??o dos dado do presente estudo. A rede Neural Gas, portanto, mostrou- se promissora para o desenvolvimento de softwares para uso na classifica??o automatizada de sistemas pulverulentos farmac?uticos

APA, Harvard, Vancouver, ISO, and other styles

46

Nair, Karthik. "Optimisation of autoencoders for prediction of SNPs determining phenotypes in wheat." Thesis, Uppsala universitet, Institutionen för biologisk grundutbildning, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-437451.

Full text

Abstract:

The increase in demand for food has resulted in increased demand for tools that help streamline plant breeding process in order to create new varieties of crops. Identifying the underlying genetic mechanism of favourable characteristics is essential in order to make the best breeding decisions. In this project we have developed a modified autoencoder model which allows for lateral phenotype injection into the latent layer, in order to identify causal SNPs for phenotypes of interest in wheat. SNP and phenotype data for 500 samples of Lantmännen SW Seed provided by Lantmännen was used to train the network. Artificial phenotype created using a single SNP was used during training instead of real phenotype, since the relationship between the phenotype and SNP is already known. The modified training model with lateral phenotype injection showed significant increase in genotype concordance of the artificial phenotype when compared to the control model without phenotype injection. Causal SNP was successfully identified by using concordance terrain graph, where the difference in concordance of individual SNPs between the modified modified model and control model was plotted against the genomic position of each SNP. The model requires further testing to elucidate its behaviour for phenotypes linked to multiple SNPs.

APA, Harvard, Vancouver, ISO, and other styles

47

McConnell, Sabine. "An unsupervised neural network for the clustering of extragalactic objects." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2002. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp05/MQ65638.pdf.

Full text

APA, Harvard, Vancouver, ISO, and other styles

48

ESTEU, BRUNO ROMANELLI MENECHINI. "CLUSTERING VIBRATION DATA FROM OIL WELLS THROUGH UNSUPERVISED NEURAL NETWORK." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2014. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=25049@1.

Full text

Abstract:

PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO
COORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIOR
PROGRAMA DE EXCELENCIA ACADEMICA
A perfuração de poços de petróleo em águas profundas tem como objetivo atingir o melhor ponto de extração de óleo e gás natural presentes em reservatórios a alguns milhares de metros no fundo do mar. Um melhor entendimento da dinâmica de perfuração através da análise de parâmetros operacionais em tempo real é importante para otimizar os processos de perfuração e reduzir seus tempos de operação. Com esse objetivo, operadoras de petróleo têm realizado grandes investimentos no desenvolvimento de ferramentas de medição e transmissão de parâmetros durante a perfuração, tais como, entre outros, o peso sobre broca, rotação da coluna e vazão do fluido de perfuração. Dentre as vantagens em se monitorar estes dados em tempo real, destaca-se a otimização de parâmetros operacionais buscando obter uma taxa de penetração satisfatória com o menor gasto de energia possível. Em uma perfuração rotativa, essa energia é muitas vezes parcialmente dissipada devido à vibração da coluna causada pela interação entre broca e formação. Nesta dissertação, com o objetivo de extrair características comuns que pudessem vir a ajudar na otimização da atividade de perfuração, foi utilizada uma técnica de redes neurais não supervisionadas para análise de uma extensa base de dados levantados ao longo de campanhas de perfuração de poços em um mesmo campo de petróleo. Os dados de campo analisados foram obtidos ao longo de perfurações de poços verticais, exclusivamente empregando brocas tipo PDC e exibindo elevados níveis de vibração torcional. O estudo realizado a partir de registros de parâmetros de perfuração, características dos poços e respostas de vibração obtidas em tempo real por ferramentas de poço, e empregando o código de mineração de dados WEKA e a plataforma computacional de análise TIBCO Spotfire, permitiu a determinação de uma curva de desgaste de broca e a influência das ferramentas de navegação no nível de severidade de vibração ao longo da perfuração.
Drilling oil wells in deep waters aims to achieve the best point of extraction of oil and natural gas reservoirs present in a few thousand meters in the seabed. A better understanding of the drilling dynamics through the analysis of real time operation parameters is important to optimize drilling process and reduce operation time. For this purpose petroleum operator companies have been made great investments in developing tools that measure and transmit parameters during drilling operation, such as the weight on bit, pipes rotation per minute and drilling fluid flow. Among the advantages to monitor this real time data there is the operational parameters optimization looking for the least expenditure of energy as possible. In a rotary drilling operation this energy is often lost partially due to column vibration caused by the interaction between bit and formation.In this master s thesis in order to extract common features that could help on the drilling operation optimization a technique using unsupervised neural networks for analyze an extensive database which was built over drilling campaigns in a big oil field . The field data analyzed were obtained during drilling vertical wells exclusively employing PDC bits and presented high levels of torcional vibration. The study was made from drilling parameters records, wells characteristics and vibration responses obtained in real time by downhole tools. Employing the WEKA data mining code and the computing analysis platform TIBCO potfire it was possible determine a bit wear curve and the real influence of navigation tools on the severity levels of vibration during drilling operations.

APA, Harvard, Vancouver, ISO, and other styles

49

CAO, BAOQIANG. "ON APPLICATIONS OF STATISTICAL LEARNING TO BIOPHYSICS." University of Cincinnati / OhioLINK, 2007. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1168577852.

Full text

APA, Harvard, Vancouver, ISO, and other styles

50

Mackenzie, Mathew David. "CDUL Class Directed Unsupervised Learning : an enhanced neural network classification system." Thesis, University of Kent, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.360970.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Dissertations / Theses on the topic 'Unsupervised neural networks'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles