Academic literature on the topic 'Learning with pre-built models'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Learning with pre-built models.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Learning with pre-built models"
1
Fauszt, Tibor, László Bognár, and Ágnes Sándor. "Increasing the Prediction Power of Moodle Machine Learning Models with Self-defined Indicators." International Journal of Emerging Technologies in Learning (iJET) 16, no. 24 (December 21, 2021): 23–39. http://dx.doi.org/10.3991/ijet.v16i24.23923.
Full textAbstract:
Starting with version 3.4 of Moodle, it has been possible to build educational ML models using predefined indicators in the Analytics API. These models can be used primarily to identify students at risk of failure. Our research shows that the goodness and predictability of models built using predefined core indicators in the API lags far behind the generally acceptable level. Moodle is an open-source system, which on the one hand allows the analysis of algorithms, and on the oth-er hand its modification and further development. Utilizing the openness of the system, we examined the calculation algorithm of the core indicators, and then, based on the experience, we built new models with our own indicators. Our re-sults show that the goodness of models built on a given course can be significant-ly improved. In the article, we discuss the development process in detail and pre-sent the results achieved.
2
Erian, Karim H., Pedro H. Regalado, and James M. Conrad. "Missing data handling for machine learning models." IAES International Journal of Robotics and Automation (IJRA) 10, no. 2 (June 1, 2021): 123. http://dx.doi.org/10.11591/ijra.v10i2.pp123-132.
Full textAbstract:
This paper discusses a novel algorithm for solving a missing data problem in the machine learning pre-processing stage. A model built to help lenders evaluate home loans based on numerous factors by learning from available user data, is adopted in this paper as an example. If one of the factors is missing for a person in the dataset, the currently used methods delete the whole entry therefore reducing the size of the dataset and affecting the machine learning model accuracy. The novel algorithm aims to avoid losing entries for missing factors by breaking the dataset into multiple subsets, building a different machine learning model for each subset, then combining the models into one machine learning model. In this manner, the model makes use of all available data and only neglects the missing values. Overall, the new algorithm improved the prediction accuracy by 5% from 93% accuracy to 98% in the home loan example.
3
Cinar, Eyup. "A Sensor Fusion Method Using Transfer Learning Models for Equipment Condition Monitoring." Sensors 22, no. 18 (September 8, 2022): 6791. http://dx.doi.org/10.3390/s22186791.
Full textAbstract:
Sensor fusion is becoming increasingly popular in condition monitoring. Many studies rely on a fusion-level strategy to enable the most effective decision-making and improve classification accuracy. Most studies rely on feature-level fusion with a custom-built deep learning architecture. However, this may limit the ability to use the widely available pre-trained deep learning architectures available to users today. This study proposes a new method for sensor fusion based on concepts inspired by image fusion. The method enables the fusion of multiple and heterogeneous sensors in the time-frequency domain by fusing spectrogram images. The method’s effectiveness is tested with transfer learning (TL) techniques on four different pre-trained convolutional neural network (CNN) based model architectures using an original test environment and data acquisition system. The results show that the proposed sensor fusion technique effectively classifies device faults and the pre-trained TL models enrich the model training capabilities.
4
Lage, Isaac, Emily Chen, Jeffrey He, Menaka Narayanan, Been Kim, Samuel J. Gershman, and Finale Doshi-Velez. "Human Evaluation of Models Built for Interpretability." Proceedings of the AAAI Conference on Human Computation and Crowdsourcing 7 (October 28, 2019): 59–67. http://dx.doi.org/10.1609/hcomp.v7i1.5280.
Full textAbstract:
Recent years have seen a boom in interest in interpretable machine learning systems built on models that can be understood, at least to some degree, by domain experts. However, exactly what kinds of models are truly human-interpretable remains poorly understood. This work advances our understanding of precisely which factors make models interpretable in the context of decision sets, a specific class of logic-based model. We conduct carefully controlled human-subject experiments in two domains across three tasks based on human-simulatability through which we identify specific types of complexity that affect performance more heavily than others–trends that are consistent across tasks and domains. These results can inform the choice of regularizers during optimization to learn more interpretable models, and their consistency suggests that there may exist common design principles for interpretable machine learning systems.
5
Yimam, Seid Muhie, Abinew Ali Ayele, Gopalakrishnan Venkatesh, Ibrahim Gashaw, and Chris Biemann. "Introducing Various Semantic Models for Amharic: Experimentation and Evaluation with Multiple Tasks and Datasets." Future Internet 13, no. 11 (October 27, 2021): 275. http://dx.doi.org/10.3390/fi13110275.
Full textAbstract:
The availability of different pre-trained semantic models has enabled the quick development of machine learning components for downstream applications. However, even if texts are abundant for low-resource languages, there are very few semantic models publicly available. Most of the publicly available pre-trained models are usually built as a multilingual version of semantic models that will not fit well with the need for low-resource languages. We introduce different semantic models for Amharic, a morphologically complex Ethio-Semitic language. After we investigate the publicly available pre-trained semantic models, we fine-tune two pre-trained models and train seven new different models. The models include Word2Vec embeddings, distributional thesaurus (DT), BERT-like contextual embeddings, and DT embeddings obtained via network embedding algorithms. Moreover, we employ these models for different NLP tasks and study their impact. We find that newly-trained models perform better than pre-trained multilingual models. Furthermore, models based on contextual embeddings from FLAIR and RoBERTa perform better than word2Vec models for the NER and POS tagging tasks. DT-based network embeddings are suitable for the sentiment classification task. We publicly release all the semantic models, machine learning components, and several benchmark datasets such as NER, POS tagging, sentiment classification, as well as Amharic versions of WordSim353 and SimLex999.
6
Wang, Chengyu, Mengli Cheng, Xu Hu, and Jun Huang. "EasyASR: A Distributed Machine Learning Platform for End-to-end Automatic Speech Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 18 (May 18, 2021): 16111–13. http://dx.doi.org/10.1609/aaai.v35i18.18028.
Full textAbstract:
We present EasyASR, a distributed machine learning platform for training and serving large-scale Automatic Speech Recognition (ASR) models, as well as collecting and processing audio data at scale. Our platform is built upon the Machine Learning Platform for AI of Alibaba Cloud. Its main functionality is to support efficient learning and inference for end-to-end ASR models on distributed GPU clusters. It allows users to learn ASR models with either pre-defined or user-customized network architectures via simple user interface. On EasyASR, we have produced state-of-the-art results over several public datasets for Mandarin speech recognition.
7
Singh, Hrithik, Shambhavi Kaushik, Shruti Talyan, and Kartikeya Dwivedi. "Skin Cancer Detection Using Deep Learning techniques." International Journal for Research in Applied Science and Engineering Technology 10, no. 5 (May 31, 2022): 4296–305. http://dx.doi.org/10.22214/ijraset.2022.43090.
Full textAbstract:
Abstract: Skin cancer detection is one of the major prob-lems across the world. Early detection of the skin cancer and its diagnosis is very important for the further treatment of it. Artificial Intelligence has progressed a lot in the field of healthcare and diagnosis and hence skin cancer can also be detected using Machine Leaning and AI. In this research, we have used convolutional neural network for image processing and recognition. The models implemented are Vgg-16, mobilenet, inceptionV3. The paper also reviewed different AI based skin cancer detection models. Here we have used transfer learning method to reuse a pre-trained model also a model from the scratch is also built using CNN blocks. A web app is also featured using HTML, Flask and CSS in which we just have to put the diagnosis image and it will predict the result. Hence, these pre-trained models and a new model from scratch are applied to procure the most optimal model to detect skin cancer using images and web app helps on getting the result at the user end. Thus, the methodology used in this paper if implemented will give improved results of early skin cancer detection using deep learning methods. Index Terms: Skin Cancer, VGG-16, deep learning, convolu-tional neural network, transfer learning.
8
Pedditzi, Maria L., and Marcello Nonnis. "Pre-service Teachers' Representations About Children's Learning: A Pilot Study." Open Psychology Journal 13, no. 1 (November 13, 2020): 315–20. http://dx.doi.org/10.2174/1874350102013010315.
Full textAbstract:
Background:Research on teachers' representations of children's learning is currently ongoing. Social representations are common-sense theories built and shared in everyday interactions. Their analysis can detect the possible differences between teachers’ naïve beliefs and scientific learning theories. Objective: The objective of this pilot study is to analyse the beliefs about children’s learning of a group of teachers. The beliefs will be related to the most acknowledged learning theories. Methods: A mixed methods research was employed to analyse 100 pre-service teachers’ representations of the origins of learning and the psychological processes involved. Results: It emerged from the results that the teachers interviewed consider children’s learning mainly as culturally acquired, which reveals the prevailing constructivist conception of learning. Many pre-service primary school teachers, however, tend to see learning as mere ‘transfer of information’; many pre-service kindergarten teachers perceive learning as ‘behaviour modification’. The most considered psychological aspects are ‘knowledge’ and ‘acquisition’, while emotions are barely considered. Conclusion: Linking implicit theories and disciplinary theories could support pre-service teachers in integrating the theory and the practice of learning so as to understand the way their models influence their educational choices.
9
Zhang, Li, Haimeng Fan, Chengxia Peng, Guozheng Rao, and Qing Cong. "Sentiment Analysis Methods for HPV Vaccines Related Tweets Based on Transfer Learning." Healthcare 8, no. 3 (August 28, 2020): 307. http://dx.doi.org/10.3390/healthcare8030307.
Full textAbstract:
The widespread use of social media provides a large amount of data for public sentiment analysis. Based on social media data, researchers can study public opinions on human papillomavirus (HPV) vaccines on social media using machine learning-based approaches that will help us understand the reasons behind the low vaccine coverage. However, social media data is usually unannotated, and data annotation is costly. The lack of an abundant annotated dataset limits the application of deep learning methods in effectively training models. To tackle this problem, we propose three transfer learning approaches to analyze the public sentiment on HPV vaccines on Twitter. One was transferring static embeddings and embeddings from language models (ELMo) and then processing by bidirectional gated recurrent unit with attention (BiGRU-Att), called DWE-BiGRU-Att. The others were fine-tuning pre-trained models with limited annotated data, called fine-tuning generative pre-training (GPT) and fine-tuning bidirectional encoder representations from transformers (BERT). The fine-tuned GPT model was built on the pre-trained generative pre-training (GPT) model. The fine-tuned BERT model was constructed with BERT model. The experimental results on the HPV dataset demonstrated the efficacy of the three methods in the sentiment analysis of the HPV vaccination task. The experimental results on the HPV dataset demonstrated the efficacy of the methods in the sentiment analysis of the HPV vaccination task. The fine-tuned BERT model outperforms all other methods. It can help to find strategies to improve vaccine uptake.
10
Achicanoy, Harold, Deisy Chaves, and Maria Trujillo. "StyleGANs and Transfer Learning for Generating Synthetic Images in Industrial Applications." Symmetry 13, no. 8 (August 16, 2021): 1497. http://dx.doi.org/10.3390/sym13081497.
Full textAbstract:
Deep learning applications on computer vision involve the use of large-volume and representative data to obtain state-of-the-art results due to the massive number of parameters to optimise in deep models. However, data are limited with asymmetric distributions in industrial applications due to rare cases, legal restrictions, and high image-acquisition costs. Data augmentation based on deep learning generative adversarial networks, such as StyleGAN, has arisen as a way to create training data with symmetric distributions that may improve the generalisation capability of built models. StyleGAN generates highly realistic images in a variety of domains as a data augmentation strategy but requires a large amount of data to build image generators. Thus, transfer learning in conjunction with generative models are used to build models with small datasets. However, there are no reports on the impact of pre-trained generative models, using transfer learning. In this paper, we evaluate a StyleGAN generative model with transfer learning on different application domains—training with paintings, portraits, Pokémon, bedrooms, and cats—to generate target images with different levels of content variability: bean seeds (low variability), faces of subjects between 5 and 19 years old (medium variability), and charcoal (high variability). We used the first version of StyleGAN due to the large number of publicly available pre-trained models. The Fréchet Inception Distance was used for evaluating the quality of synthetic images. We found that StyleGAN with transfer learning produced good quality images, being an alternative for generating realistic synthetic images in the evaluated domains.
Dissertations / Theses on the topic "Learning with pre-built models"
1
Thompson, Kate. "Models as mindtools for environmental education: How do students use models to learn about a complex socio-environmental system?" University of Sydney, 2008. http://hdl.handle.net/2123/3608.
Full textAbstract:
Doctor of Philosophy (PhD)Environmental issues are complex and understanding them involves integration of different areas of knowledge, feedback and time delays, however strategies to cope with complexity are not often used or taught in environmental education. The aim of this thesis is to examine the benefit of three such strategies for environmental education: multiple external representations, learning from models, and collaborative learning. The socio-environmental system modelled was visitor impact in a national park in Australia. Students in Year 9 and 10 from two schools were given a text description (Text group) and either a system dynamics model (SDM group), an agent-based model (ABM group), or both models (SDM & ABM group). This experimental design allowed learning outcomes (environmental and system dynamics knowledge, and understanding of the socio-environmental system) and use of the model(s) (in terms of the proportion of time spent on each screen, activities, and strategies) to be compared in each learning environment (individual and collaborative). Multiple external representations were the most successful strategy in the individual learning environment in terms of increases in environmental knowledge. However, students given only the system dynamics model had greater understanding of the system, and students given only the agent-based model increased environmental knowledge easily identified in the animated representation. Prior knowledge, patterns of use, strategies for changing variables and the representational affordances of the models explained some of these differences. In particular, prior knowledge was an important indicator of how students coordinated use of the models in the SDM & ABM group. Learning with a system dynamics model was the most successful strategy for students in the collaborative learning environment. Differences between the learning environments were detected in all groups with respect to both learning outcomes and use of the models due to prior knowledge, interrogation of the models, and the learning environments themselves. These experiments have provided evidence that strategies for understanding complex systems provide viable methods of communicating complex ideas to school-aged students with varying levels of prior knowledge. In particular, multiple external representations provided students with flexibility in how they learned; models allowed students to experiment with a system otherwise not allowed; and a collaborative learning environment facilitated students’ interpretation of a system dynamics model.
2
Thompson, Kate. "Models as mindtools for environmental education: How do students use models to learn about a complex socio-environmental system?" Thesis, The University of Sydney, 2007. http://hdl.handle.net/2123/3608.
Full textAbstract:
Environmental issues are complex and understanding them involves integration of different areas of knowledge, feedback and time delays, however strategies to cope with complexity are not often used or taught in environmental education. The aim of this thesis is to examine the benefit of three such strategies for environmental education: multiple external representations, learning from models, and collaborative learning. The socio-environmental system modelled was visitor impact in a national park in Australia. Students in Year 9 and 10 from two schools were given a text description (Text group) and either a system dynamics model (SDM group), an agent-based model (ABM group), or both models (SDM & ABM group). This experimental design allowed learning outcomes (environmental and system dynamics knowledge, and understanding of the socio-environmental system) and use of the model(s) (in terms of the proportion of time spent on each screen, activities, and strategies) to be compared in each learning environment (individual and collaborative). Multiple external representations were the most successful strategy in the individual learning environment in terms of increases in environmental knowledge. However, students given only the system dynamics model had greater understanding of the system, and students given only the agent-based model increased environmental knowledge easily identified in the animated representation. Prior knowledge, patterns of use, strategies for changing variables and the representational affordances of the models explained some of these differences. In particular, prior knowledge was an important indicator of how students coordinated use of the models in the SDM & ABM group. Learning with a system dynamics model was the most successful strategy for students in the collaborative learning environment. Differences between the learning environments were detected in all groups with respect to both learning outcomes and use of the models due to prior knowledge, interrogation of the models, and the learning environments themselves. These experiments have provided evidence that strategies for understanding complex systems provide viable methods of communicating complex ideas to school-aged students with varying levels of prior knowledge. In particular, multiple external representations provided students with flexibility in how they learned; models allowed students to experiment with a system otherwise not allowed; and a collaborative learning environment facilitated students’ interpretation of a system dynamics model.
3
Bitter, James. "Integrative Family Therapy and Counseling: Advanced Practices Across Multiple Theoretical Models (Pre-Convention Learning Institute)." Digital Commons @ East Tennessee State University, 2009. https://dc.etsu.edu/etsu-works/6111.
Full text
4
Jahanshahi, Kaveh. "Quantification of the influences of built-form upon travel of employed adults : new models based on the UK National Travel Survey." Thesis, University of Cambridge, 2017. https://www.repository.cam.ac.uk/handle/1810/267841.
Full textAbstract:
After decades of research, a host of analytical difficulties is still hindering our understanding of the influences of the built form on travel. The main challenges are (a) assembling good quality data that reflects the majority of the known influences and that supports continuous monitoring, and (b) making sense methodologically of the many variables which strongly intercorrelate. This study uses the UK national travel survey (NTS) data that is among the most comprehensive of its form in the world. The fact that it has rarely been used so far for this purpose may be attributable to the methodological difficulties. This dissertation aims to develop a new analytical framework based on extended structural equation models (SEMs) in order to overcome some of the key methodological difficulties in quantifying the influences of the built form on travel, and in addition to provide a means to continuously monitor any changes in the effects over time. The analyses are focused on employed adults, because they are not only the biggest UK population segment with the highest per capita travel demand, but also the segment that are capable of adapting more rapidly to changing land use, built form and transport supply conditions. The research is pursued through three new models. Model 1 is a path diagram coupled with factor analyses, which estimates continuous, categorical and binary dependent variables. The model estimates the influences on travel distance, time and trip frequency by trip purpose while accounting for self-selection, spatial sorting, endogeneity of car ownership, and interactions among trip purposes. The results highlight stark differences among commuters, particularly the mobility disadvantages of women, part time and non-car owning workers even when they live in the most accessible urban areas. Model 2 incorporates latent categorisation analyses in order to identify a tangible typology of the built form and the associated variations in impacts on travel. Identifying NTS variables as descriptors for tangible built form categories provides an improved basis for investigating land use and transport planning interventions. The model reveals three distinct built form categories in the UK with striking variations in the patterns of influences. Model 3 further investigates the variations across the built form categories. The resulting random intercept SEM provides a more precise quantification of the influences of self-selection and spatial sorting across the built form categories for each socioeconomic group. Four research areas are highlighted for further studies: First, new preference, attitude and behavioural parameters may be introduced through incorporating non-NTS behavioural surveys; Second, the new SEMs provide a basis for incorporating choice modelling where the utility function is defined with direct, indirect and latent variables; Third, conceptual and methodological developments – such as non-parametric latent class analysis, allow expanding the current model to monitor changes in travel behaviour as and when new NTS or non NTS data become available. Fourth, the robustness of the inferences regarding causal or directional influences may require further quantification through designing new panel data sets, building on the findings above.
5
Dureckova, Hana. "Robust Machine Learning QSPR Models for Recognizing High Performing MOFs for Pre-Combustion Carbon Capture and Using Molecular Simulation to Study Adsorption of Water and Gases in Novel MOFs." Thesis, Université d'Ottawa / University of Ottawa, 2018. http://hdl.handle.net/10393/37288.
Full textAbstract:
Metal organic frameworks (MOFs) are a class of nanoporous materials composed through self-assembly of inorganic and organic structural building units (SBUs). MOFs show great promise for many applications due to their record-breaking internal surface areas and tunable pore chemistry. This thesis work focuses on gas separation applications of MOFs in the context of carbon capture and storage (CCS) technologies. CCS technologies are expected to play a key role in the mitigation of anthropogenic CO2 emissions in the near future. In the first part of the thesis, robust machine learning quantitative structure-property relationship (QSPR) models are developed to predict CO2 working capacity and CO2/H2 selectivity for pre-combustion carbon capture using the most topologically diverse database of hypothetical MOF structures constructed to date (358,400 MOFs, 1166 network topologies). The support vector regression (SVR) models are developed on a training set of 35,840 MOFs (10% of the database) and validated on the remaining 322,560 MOFs. The most accurate models for CO2 working capacities (R2 = 0.944) and CO2/H2 selectivities (R2 = 0.876) are built from a combination of six geometric descriptors and three novel y-range normalized atomic-property-weighted radial distribution function (AP-RDF) descriptors. 309 common MOFs are identified between the grand canonical Monte Carlo (GCMC) calculated and SVR-predicted top-1000 high-performing MOFs ranked according to a normalized adsorbent performance score. This work shows that SVR models can indeed account for the topological diversity exhibited by MOFs.
In the second project of this thesis, computational simulations are performed on a MOF, CALF-20, to examine its chemical and physical properties which are linked to its exceptional water-resisting ability. We predict the atomic positions in the crystal structure of the bulk phase of CALF-20, for which only a powder X-ray diffraction pattern is available, from a single crystal X-ray diffraction pattern of a metastable phase of CALF-20. Using the predicted CALF-20 structure, we simulate adsorption isotherms of CO2 and N2 under dry and humid conditions which are in excellent agreement with experiment. Snapshots of the CALF-20 undergoing water sorption simulations reveal that water molecules in a given pore adsorb and desorb together due to hydrogen bonding. Binding sites and binding energies of CO2 and water in CALF-20 show that the preferential CO2 uptake at low relative humidities is driven by the stronger binding energy of CO2 in the MOF, and the sharp increase in water uptake at higher relative humidities is driven by the strong intermolecular interactions between water.
In the third project of this thesis, we use computational simulations to investigate the effects of residual solvent on Ni-BPM’s CH4 and N2 adsorption properties. Single crystal X-ray diffraction data shows that there are two sets of positions (Set 1 and 2) that can be occupied by the 10 residual DMSO molecules in the Ni-BPM framework. GCMC simulations of CH4 and N2 uptake in Ni-BPM reveal that CH4 uptake is in closest agreement with experiment when the 10 DMSO’s are placed among the two sets of positions in equal ratio (Mixed Set). Severe under-prediction and over-prediction of CH4 uptake are observed when the DMSO’s are placed in Set1 and Set 2 positions, respectively. Through binding site analysis, the CH4 binding sites within the Ni-BPM framework are found to overlap with the Set 1 DMSO positions but not with the Set 2 DMSO positions which explains the deviations in CH4 uptake observed for these cases. Binding energy calculations reveal that CH4 molecules are most stabilized when the DMSO’s are in the Mixed Set of positions.
6
Holm, Henrik. "Bidirectional Encoder Representations from Transformers (BERT) for Question Answering in the Telecom Domain. : Adapting a BERT-like language model to the telecom domain using the ELECTRA pre-training approach." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-301313.
Full textAbstract:
The Natural Language Processing (NLP) research area has seen notable advancements in recent years, one being the ELECTRA model which improves the sample efficiency of BERT pre-training by introducing a discriminative pre-training approach. Most publicly available language models are trained on general-domain datasets. Thus, research is lacking for niche domains with domain-specific vocabulary. In this paper, the process of adapting a BERT-like model to the telecom domain is investigated. For efficiency in training the model, the ELECTRA approach is selected. For measuring target- domain performance, the Question Answering (QA) downstream task within the telecom domain is used. Three domain adaption approaches are considered: (1) continued pre- training on telecom-domain text starting from a general-domain checkpoint, (2) pre-training on telecom-domain text from scratch, and (3) pre-training from scratch on a combination of general-domain and telecom-domain text. Findings indicate that approach 1 is both inexpensive and effective, as target- domain performance increases are seen already after small amounts of training, while generalizability is retained. Approach 2 shows the highest performance on the target-domain QA task by a wide margin, albeit at the expense of generalizability. Approach 3 combines the benefits of the former two by achieving good performance on QA both in the general domain and the telecom domain. At the same time, it allows for a tokenization vocabulary well-suited for both domains. In conclusion, the suitability of a given domain adaption approach is shown to depend on the available data and computational budget. Results highlight the clear benefits of domain adaption, even when the QA task is learned through behavioral fine-tuning on a general-domain QA dataset due to insufficient amounts of labeled target-domain data being available.Dubbelriktade språkmodeller som BERT har på senare år nått stora framgångar inom språkteknologiområdet. Flertalet vidareutvecklingar av BERT har tagits fram, bland andra ELECTRA, vars nyskapande diskriminativa träningsprocess förkortar träningstiden. Majoriteten av forskningen inom området utförs på data från den allmänna domänen. Med andra ord finns det utrymme för kunskapsbildning inom domäner med områdesspecifikt språk. I detta arbete utforskas metoder för att anpassa en dubbelriktad språkmodell till telekomdomänen. För att säkerställa hög effektivitet i förträningsstadiet används ELECTRA-modellen. Uppnådd prestanda i måldomänen mäts med hjälp av ett frågebesvaringsdataset för telekom-området. Tre metoder för domänanpassning undersöks: (1) fortsatt förträning på text från telekom-området av en modell förtränad på den allmänna domänen; (2) förträning från grunden på telekom-text; samt (3) förträning från grunden på en kombination av text från telekom-området och den allmänna domänen. Experimenten visar att metod 1 är både kostnadseffektiv och fördelaktig ur ett prestanda-perspektiv. Redan efter kort fortsatt förträning kan tydliga förbättringar inom frågebesvaring inom måldomänen urskiljas, samtidigt som generaliserbarhet kvarhålls. Tillvägagångssätt 2 uppvisar högst prestanda inom måldomänen, om än med markant sämre förmåga att generalisera. Metod 3 kombinerar fördelarna från de tidigare två metoderna genom hög prestanda dels inom måldomänen, dels inom den allmänna domänen. Samtidigt tillåter metoden användandet av ett tokenizer-vokabulär väl anpassat för båda domäner. Sammanfattningsvis bestäms en domänanpassningsmetods lämplighet av den respektive situationen och datan som tillhandahålls, samt de tillgängliga beräkningsresurserna. Resultaten påvisar de tydliga vinningar som domänanpassning kan ge upphov till, även då frågebesvaringsuppgiften lärs genom träning på ett dataset hämtat ur den allmänna domänen på grund av otillräckliga mängder frågebesvaringsdata inom måldomänen.
7
Bjöörn, Anton. "Employing a Transformer Language Model for Information Retrieval and Document Classification : Using OpenAI's generative pre-trained transformer, GPT-2." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-281766.
Full textAbstract:
As the information flow on the Internet keeps growing it becomes increasingly easy to miss important news which does not have a mass appeal. Combating this problem calls for increasingly sophisticated information retrieval methods. Pre-trained transformer based language models have shown great generalization performance on many natural language processing tasks. This work investigates how well such a language model, Open AI’s General Pre-trained Transformer 2 model (GPT-2), generalizes to information retrieval and classification of online news articles, written in English, with the purpose of comparing this approach with the more traditional method of Term Frequency-Inverse Document Frequency (TF-IDF) vectorization. The aim is to shed light on how useful state-of-the-art transformer based language models are for the construction of personalized information retrieval systems. Using transfer learning the smallest version of GPT-2 is trained to rank and classify news articles achieving similar results to the purely TF-IDF based approach. While the average Normalized Discounted Cumulative Gain (NDCG) achieved by the GPT-2 based model was about 0.74 percentage points higher the sample size was too small to give these results high statistical certainty.Informationsflödet på Internet fortsätter att öka vilket gör det allt lättare att missa viktiga nyheter som inte intresserar en stor mängd människor. För att bekämpa detta problem behövs allt mer sofistikerade informationssökningsmetoder. Förtränade transformermodeller har sedan ett par år tillbaka tagit över som de mest framstående neurala nätverken för att hantera text. Det här arbetet undersöker hur väl en sådan språkmodell, Open AIs General Pre-trained Transformer 2 (GPT-2), kan generalisera från att generera text till att användas för informationssökning och klassificering av texter. För att utvärdera detta jämförs en transformerbaserad modell med en mer traditionell Term Frequency- Inverse Document Frequency (TF-IDF) vektoriseringsmodell. Målet är att klargöra hur användbara förtränade transformermodeller faktiskt är i skapandet av specialiserade informationssökningssystem. Den minsta versionen av språkmodellen GPT-2 anpassas och tränas om till att ranka och klassificera nyhetsartiklar, skrivna på engelska, och uppnår liknande prestanda som den TF-IDF baserade modellen. Den GPT-2 baserade modellen hade i genomsnitt 0.74 procentenheter högre Normalized Discounted Cumulative Gain (NDCG) men provstorleken var ej stor nog för att ge dessa resultat hög statistisk säkerhet.
8
Gustafson, Nathaniel Lee. "A Confidence-Prioritization Approach to Data Processing in Noisy Data Sets and Resulting Estimation Models for Predicting Streamflow Diel Signals in the Pacific Northwest." BYU ScholarsArchive, 2012. https://scholarsarchive.byu.edu/etd/3294.
Full textAbstract:
Streams in small watersheds are often known to exhibit diel fluctuations, in which streamflow oscillates on a 24-hour cycle. Streamflow diel fluctuations, which we investigate in this study, are an informative indicator of environmental processes. However, in Environmental Data sets, as well as many others, there is a range of noise associated with individual data points. Some points are extracted under relatively clear and defined conditions, while others may include a range of known or unknown confounding factors, which may decrease those points' validity. These points may or may not remain useful for training, depending on how much uncertainty they contain. We submit that in situations where some variability exists in the clarity or 'Confidence' associated with individual data points – Notably environmental data – an approach that factors this confidence into account during the training phase is beneficial. We propose a methodological framework for assigning confidence to individual data records and augmenting training with that information. We then exercise this methodology on two separate datasets: A simulated data set, and a real-world, Environmental Science data set with a focus on streamflow diel signals. The simulated data set provides integral understanding of the nature of the data involved, and the Environmental Science data set provides a real-world case study of an application of this methodology against noisy data. Both studies' results indicate that applying and utilizing confidence in training increases performance and assists in the Data Mining Process.
9
Bokosmaty, Rena. "Student learning experiences with the online component of a partially flipped teaching model." Thesis, The University of Sydney, 2022. https://hdl.handle.net/2123/29916.
Full textAbstract:
Flipped learning has received increased recognition as an innovative pedagogical approach that has the potential to improve students’ learning experience in higher education. This approach creates a ‘reversed’ learning experience, where portions of the didactic lecture traditionally presented in class is moved online in the form of pre-learning materials. There is increasing evidence that this leads to improvements in academic performance with the online pre-learning materials being an underlying factor.
This thesis reports student behavioural engagement, behavioural patterns, and approaches to learning with the online component of a partially flipped learning model and its impact on student academic performance in chemistry courses. An engagement index was developed to quantify student engagement levels with pre-learning materials. The findings revealed higher levels of engagement led to significant improvements in academic performance. Several patterns were detected when measuring students’ frequency of access for each of the pre-learning materials. The dominant pattern revealed that students tend to favour accessing a pre-learning quiz more frequently than the video. Most students self-identified to be strategic learners and were categorised to be moderately or highly engaged with a preference to accessing the quizzes more frequently than the videos. Students reported that weighting of the quizzes, although low, was a motivating factor for completion. The most pronounced differences in academic performance were observed in the mainstream rather than advanced courses, suggesting that the online component mainly benefited students with lower proficiency levels of chemistry. Recommendations regarding the design of the pre-learning materials were proposed to enhance student engagement, encourage the desired behavioural pattern and adoption of a deep learning approach.
10
Nivens, Ryan Andrew, and Renée Rice Moran. "Beyond Problem-Based Learning: How a Residency Model Improves the Education of Pre-Service Teachers." Digital Commons @ East Tennessee State University, 2015. https://dc.etsu.edu/etsu-works/221.
Full textBooks on the topic "Learning with pre-built models"
1
Learning through the built environment: An ecological approach to child development. New York: Irvington Pub., 1985.
Find full text
2
Polyakova, Anna, Tat'yana Sergeeva, and Irina Kitaeva. The continuous formation of the stochastic culture of schoolchildren in the context of the digital transformation of general education. ru: INFRA-M Academic Publishing LLC., 2022. http://dx.doi.org/10.12737/1876368.
Full textAbstract:
The material presented in the monograph shows the possibilities of continuous teaching of mathematics at school, namely, the significant potential of modern information and communication technologies, with the help of which it is possible to form elements of stochastic culture among students. Continuity in learning is considered from two positions: procedural and educational-cognitive. In addition, a distinctive feature of the book is the presentation of the digital transformation of general education as a way to overcome the "new digital divide". Methodological features of promising digital technologies (within the framework of teaching students the elements of the probabilistic and statistical line) that contribute to overcoming the "new digital divide": artificial intelligence, the Internet of Things, additive manufacturing, machine learning, blockchain, virtual and augmented reality are described.
The solution of the main questions of probability theory and statistics in the 9th grade mathematics course is proposed to be carried out using a distance learning course built in the Moodle distance learning system. The content, structure and methodological features of the implementation of the stochastics course for students of grades 10-11 of a secondary school are based on the use of such tools in the educational process as an online calculator for plotting functions, the Wolfram Alpha service, Google Docs and Google Tables services, the Yaklass remote training, the Banktest website.<url>", interactive module "Galton Board", educational website "Mathematics at school".
It will be interesting for students, undergraduates, postgraduates, mathematics teachers, as well as specialists improving their qualifications in the field of pedagogical education.
3
RE, Marena Simmons Jones, and Maurice Geddis MA AMFT/APCC. Cllaimm© Model: Optimal Results Maximizing True Potential for Student Learning Preschool Through Pre-Adolesent. Author Solutions, LLC, 2022.
Find full text
4
RE, Marena Simmons Jones, and Maurice Geddis MA AMFT/APCC. Cllaimm© Model: Optimal Results Maximizing True Potential for Student Learning Preschool Through Pre-Adolesent. Author Solutions, LLC, 2022.
Find full text
5
Regelski, Thomas A. Curriculum Philosophy and Theory for Music Education Praxis. Oxford University Press, 2021. http://dx.doi.org/10.1093/oso/9780197558690.001.0001.
Full textAbstract:
Curriculum Philosophy and Theory for Music Education Praxis is offered for advanced pre-service music education students, in-service teachers, and doctoral students. “Curriculum” is often poorly understood by music teachers. It also is a typically ignored topic in their teacher training where emphasis is on “methods,” but without prior planning of the musical goals those methods supposedly serve. The basic question of curriculum planning in this book, “What of all that could be taught is most worth learning?,” is not usually what teachers usually have in mind. In any case, too often their answers are not supportable by the rigorous philosophical and theoretical scholarship of this monograph. The result is the present anarchy of “programs” that fails to promote pragmatic and long-lasting results. This leads to the ever-growing “legitimation crisis” that advertises the aesthetic benefits of music education in schools. However, since these benefits are vague and intangible, music teachers constantly must engage in “advocacy” of their “programs.” This scholarly monograph accepts that pre- and in-service readers can understand the challenges of curriculum planning. It begins with a brisk survey of philosophies of music and music education inherited from the Greeks—included because they too often still dominate contemporary music teaching in negative ways. Then more recent and substantial bases of music curriculum and praxis theory of music and music education are examined as alternatives for planning curriculum built on intellectually substantial philosophical and theoretical grounds. The study concludes with a model curriculum based on recent praxis theory where musical and educational benefits are evident to students, administrators, and taxpayers and lead to “artful” living through music.
6
Schuldberg, David, Ruth Richards, and Shan Guisinger, eds. Chaos and Nonlinear Psychology. Oxford University Press, 2022. http://dx.doi.org/10.1093/oso/9780190465025.001.0001.
Full textAbstract:
This book, for psychologists, clinicians, social scientists, and the general reader, reveals how chaos and nonlinear dynamics can bring new understanding to everyday topics in social sciences. Contributors are leaders in the intersection of psychology and chaos and complexity theories. Written first for the curious and the nonspecialist, while adding areas for those with a more extensive background, this book offers openness and creative wonder. It is conceptual and user-friendly, built around six themes—which are the main learnings for readers. These are (1) seeing nonlinearity, (2) appreciating emergence, (3) finding patterns, (4) using simple models, (5) intervening nonlinearly, and (6) considering new worldviews. It takes no specialized study—although there is more sophisticated material and optional math for those wishing it; the techie will, in addition, find concepts and diagrams to ponder. The volume intends to engage, at times may startle—whether about the weather, internet, organizations, family dynamics, health, evolution, or falling in love. It reveals how many social, personal, clinical, research, and life phenomena become understandable and can be modeled in the light of nonlinear dynamical systems theory. It even offers a broadening worldview, happening already in other sciences, toward a more dynamic, interconnected, and evolving picture, including process-oriented appreciation of one’s own experience. Readers meet the themes in different guises while learning to read subtle signs and patterns, and intervene like an aikido master in the flow of our dynamic world. The themes, are woven throughout diverse applications and extended in the integrative conclusions.
7
Koyama, Dennis, ed. Development of Innovative Pedagogical Practices for a Modern Learning Experience. CSMFL Publications, 2021. http://dx.doi.org/10.46679/9788194848363.
Full textAbstract:
In the current volume, the selected studies have been grouped into three thematic sections, presenting readers with a set of distinct but related research on meaningful issues for a modern learning experience. The first three chapters present professional and teacher development perspectives and collectively shed light on how to develop, maintain, and improve pre and in-service teacher training and professional development. The second set of four chapters provide research findings that describe the results of direct applications of modern learning elements through course assignments and teaching approaches. The final five chapters focus on critical thinking and range in their focus from classroom-based studies to full-scale curriculum reform. The collection of chapters presented in this volume represents the eclectic nature of modern learning experiences and demonstrate its applicability across educational contexts and disciplines. It is my hope that the chapters will resonate with other educational researchers in search of novel ways of creating, facilitating, and investigating modern learning experiences.
8
Cole, Ester, and Maria Kokai, eds. Consultation and Mental Health Interventions in School Settings. Hogrefe Publishing, 2021. http://dx.doi.org/10.1027/00583-000.
Full textAbstract:
This unique volume by leading educational practitioners and academics has been designed to meet the ever-growing challenges faced by educational systems in addressing the mental health, learning, and socialization needs of students. Using a unique and comprehensive consultation and intervention model, the book provides evidence-based guidance that interlinks primary, secondary, and tertiary prevention and intervention applications that allow for systematic consultation, planning, and cost-effective services. The clear and easy to apply model is used to look at specific student needs that are commonly encountered in schools (e.g., depression, ADHD, giftedness) and at issues that require school-level interventions (e.g., diversity, promoting resilience). Practitioners will appreciate the numerous downloadable practical resources and tools for hands-on applications that are available online to purchasers of the book. This book is an invaluable resource for school psychologists and mental health service providers, as well as for academics involved in training pre-service practitioners.A comprehensive guide to meeting the psychological needs of students in school settings This unique volume by leading educational practitioners and academics has been designed to meet the ever-growing challenges faced by educational systems in addressing the mental health, learning, and socialization needs of students. Using a unique and comprehensive consultation and intervention model, the book provides evidence-based guidance that interlinks primary, secondary, and tertiary prevention and intervention applications that allow for systematic consultation, planning, and cost-effective services. The clear and easy to apply model is used to look at specific student needs that are commonly encountered in schools (e.g., depression, ADHD, giftedness) and at issues that require school-level interventions (e.g., diversity, promoting resilience). Practitioners will appreciate the numerous downloadable practical resources and tools for hands-on applications that are available online to purchasers of the book. This book is an invaluable resource for school psychologists and mental health service providers, as well as for academics involved in training pre-service practitioners.
9
Kissane, David W., Barry D. Bultz, Phyllis N. Butow, Carma L. Bylund, Simon Noble, and Susie Wilkinson, eds. Oxford Textbook of Communication in Oncology and Palliative Care. Oxford University Press, 2017. http://dx.doi.org/10.1093/med/9780198736134.001.0001.
Full textAbstract:
This textbook integrates clinical wisdom with empirical findings, drawing upon the history of communication science, providing a comprehensive curriculum for applied communication skills training for specialist oncologists, surgeons, nurses, psychosocial care providers and other members of the multidisciplinary team. This new edition presents a curriculum for nurses, which discusses needs of pre-registration to advanced trainees, including the ‘SAGE & THYME’ training programme, chronic disease, responding to depressed patients, the last hours and days of life, family care, facilitation training, and e-learning. The core curriculum ranges from breaking bad news, discussing risk and prognosis, achieving shared treatment decisions, responding to difficult emotions, dealing with denial, communicating with relatives and conducting a family meeting, helping patients cope with survivorship, deal with recurrence, transition to palliative care, and talk openly about death and dying. Modules offer guidelines about key skills, essential tasks, effective strategies, and scenarios for training sessions with simulated patients. The communication science section covers the history and models of communication skills training, the art of facilitating skill development, ethics, gender, power, the internet, audio-recording significant consultations, decision aides, and shared treatment decisions, medical student training, and enhancing patient participation in consultations. Specialty issues are explored, including enrolling in clinical trials, working in teams, discussing genetic risk, reconstructive and salvage surgery, among many other important issues. Variations in clinical disciplines are also discussed, including chapters for social workers, radiologists, surgical oncologists, medical and radiation oncologists, palliative medicine, pastoral care, pharmacy, paediatrics, and the elderly.
10
Janssen, Markus, and Thomas Wiedenhorn, eds. School adoption in teacher education. Waxmann Verlag GmbH, 2020. http://dx.doi.org/10.31244/9783830992639.
Full textAbstract:
School adoption is an ambitious and innovative partnership model in teacher education which offers unique opportunities for in-service and pre-service teachers. At its core, teachers leave their school to be adopted by teacher students for one week. While the teachers engage in a professional development course outside the school, they are fully substituted by teacher students, who thus have an increased responsibility for the pupils’ learning, for the organizational matters of the school and for their own professional development. In this volume, we present different international concepts of school adoption, lessons learned, and first theoretical considerations. With it, we invite teacher educators in schools, universities, and other institutions to engage into a dialogue about the perspectives school adoption offers for teacher education and teacher education research.
Book chapters on the topic "Learning with pre-built models"
1
Kamath, Sanjay, Brigitte Grau, and Yue Ma. "How to Pre-train Your Model? Comparison of Different Pre-training Models for Biomedical Question Answering." In Machine Learning and Knowledge Discovery in Databases, 646–60. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-43887-6_58.
Full text
2
Seshu Babu, G., T. K. Sachin Saj, V. Sowmya, and K. P. Soman. "Tuberculosis Classification Using Pre-trained Deep Learning Models." In Advances in Automation, Signal Processing, Instrumentation, and Control, 767–74. Singapore: Springer Singapore, 2021. http://dx.doi.org/10.1007/978-981-15-8221-9_71.
Full text
3
Zhang, Luxin, Pascal Germain, Yacine Kessaci, and Christophe Biernacki. "Target to Source Coordinate-Wise Adaptation of Pre-trained Models." In Machine Learning and Knowledge Discovery in Databases, 378–94. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-67658-2_22.
Full text
4
Wildgans-Lang, Angelika, Sarah Scheuerer, Andreas Obersteiner, Frank Fischer, and Kristina Reiss. "Learning to Diagnose Primary Students’ Mathematical Competence Levels and Misconceptions in Document-Based Simulations." In Learning to Diagnose with Simulations, 17–31. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-89147-3_3.
Full textAbstract:
AbstractAnalyzing students’ documents (e.g., their homework) can serve as a basis for diagnosing students’ learning status and thus also for adaptive teaching. When making diagnostic judgments about students’ learning status in mathematics, teachers may benefit from using theoretical models of mathematical competence because such models illustrate what tasks students should have mastered on each level of competence. Based on students’ documents and a model of mathematical competence at the primary level, we developed a simulated learning environment for (1) analyzing and (2) supporting pre-service teachers’ diagnostic processes and results. When working in the simulated environment, pre-service elementary teachers are asked to assess virtual third graders’ learning status by diagnosing their mathematical competence levels as well as their misconceptions (e.g., misconception regarding multiplication) based on the competence model. To do so, pre-service teachers analyze students’ solutions to mathematical problems that they can select from a set of problems varying in content and difficulty. First data analyses suggest that the environment can capture differences in pre-service teachers’ diagnostic processes. A better understanding of these processes can serve as a basis for further developing the learning environment.
5
Carneiro, Gustavo, Jacinto Nascimento, and Andrew P. Bradley. "Unregistered Multiview Mammogram Analysis with Pre-trained Deep Learning Models." In Lecture Notes in Computer Science, 652–60. Cham: Springer International Publishing, 2015. http://dx.doi.org/10.1007/978-3-319-24574-4_78.
Full text
6
Wu, Yuxuan, Ding Wang, Yunkai Zou, and Ziyi Huang. "Improving Deep Learning Based Password Guessing Models Using Pre-processing." In Information and Communications Security, 163–83. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-15777-6_10.
Full text
7
Li, Bangqi, Boci Peng, Yifeng Shao, and Zhichun Wang. "Prerequisite Learning with Pre-trained Language and Graph Embedding Models." In Natural Language Processing and Chinese Computing, 98–108. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-88483-3_8.
Full text
8
van Kampen, Paul. "A Workshop Approach to Pre-service Physics Teacher Education." In Concepts, Strategies and Models to Enhance Physics Teaching and Learning, 171–80. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-18137-6_15.
Full text
9
Hire, Dnyanda N., and A. V. Patil. "Pre-trained deep learning models for content-based image classification and retrieval." In Application of Communication Computational Intelligence and Learning, 114–26. London: Routledge, 2022. http://dx.doi.org/10.1201/9781003340867-12.
Full text
10
Yang, Guanqun, Shay Dineen, Zhipeng Lin, and Xueqing Liu. "Few-Sample Named Entity Recognition for Security Vulnerability Reports by Fine-Tuning Pre-trained Language Models." In Deployable Machine Learning for Security Defense, 55–78. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-87839-9_3.
Full textConference papers on the topic "Learning with pre-built models"
1
Wu, Tz-Ying, Gurumurthy Swaminathan, Zhizhong Li, Avinash Ravichandran, Nuno Vasconcelos, Rahul Bhotika, and Stefano Soatto. "Class-Incremental Learning with Strong Pre-trained Models." In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2022. http://dx.doi.org/10.1109/cvpr52688.2022.00938.
Full text
2
Atanassov, Atanas, and Dimitar Pilev. "Pre-trained Deep Learning Models for Facial Emotions Recognition." In 2020 International Conference Automatics and Informatics (ICAI). IEEE, 2020. http://dx.doi.org/10.1109/icai50593.2020.9311334.
Full text
3
Wang, Chengyu, Haojie Pan, Minghui Qiu, Jun Huang, Fei Yang, and Yin Zhang. "Meta Distant Transfer Learning for Pre-trained Language Models." In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA, USA: Association for Computational Linguistics, 2021. http://dx.doi.org/10.18653/v1/2021.emnlp-main.768.
Full text
4
Lee, Kuan-Ying, Yuanyi Zhong, and Yu-Xiong Wang. "Do Pre-trained Models Benefit Equally in Continual Learning?" In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, 2023. http://dx.doi.org/10.1109/wacv56688.2023.00642.
Full text
5
Marquez, Freddy J. "Drilling Optimization Applying Machine Learning Regression Algorithms." In Offshore Technology Conference. OTC, 2021. http://dx.doi.org/10.4043/30934-ms.
Full textAbstract:
Abstract Machine Learning is an artificial intelligence subprocess applied to automatically and quickly perform mathematical calculations to data in order to build models used to make predictions. Technical papers related to machine learning algorithms applications have being increasingly published in many oil and gas disciplines over the last five years, revolutionizing the way engineers approach to their works, and sharing innovating solutions that contributes to an increase in efficiency. In this paper, Machine Learning models are built to predict inverse rate of penetration (ROPI) and surface torque for a well located at Gulf of Mexico shallow waters. Three type of analysis were performed. Pre-drill analysis, predicting the parameters without any data of the target well in the database. Drilling analysis, running the model every sixty meters, updating the database with information of the target well and predicting the parameters ahead the bit. Sensitivity parameter optimization analysis was performed iterating weight on bit and rotary speed values as model inputs in order identify the optimum combination to deliver the best drilling performance under the given conditions. The Extreme Gradient Boosting (XGBoost) library in Python programming language environment, was used to build the models. Model performance was satisfactory, overcoming the challenge of using drilling parameters input manually by drilling bit engineers. The database was built with data from different fields and wells. Two databases were created to build the models, one of the models did not consider logging while drilling (LWD) data in order to determine its importance on the predictions. Pre-drill surface torque prediction showed better performance than ROPI. Predictions ahead the bit performance was good both for torque and ROPI. Sensitivity parameter optimization showed better resolution with the database that includes LWD data.
6
Zarzuelo Romero, Carmen, Alejandro López-Ruiz, Manuel Díez-Minguito, Antonio Moñino, Pedro Magaña, and Miguel Ortega-Sánchez. "INTRODUCING GRADUATE STUDENTS INTO PRE-PROCESSING TECHNIQUES FOR ADVANCED NUMERICAL MODELS: APPLICATION TO HYDRODYNAMIC MODELS." In International Conference on Education and New Learning Technologies. IATED, 2016. http://dx.doi.org/10.21125/edulearn.2016.0285.
Full text
7
Alshalali, Tagrid, and Darsana Josyula. "Fine-Tuning of Pre-Trained Deep Learning Models with Extreme Learning Machine." In 2018 International Conference on Computational Science and Computational Intelligence (CSCI). IEEE, 2018. http://dx.doi.org/10.1109/csci46756.2018.00096.
Full text
8
Iyer, Vasanth, Alex J. Aved, Todd B. Howlett, Jeffrey T. Carlo, Asif Mehmood, Niki Pissniou, and S. Sitharama Iyengar. "Fast multi-modal reuse: co-occurrence pre-trained deep learning models." In Real-Time Image Processing and Deep Learning 2019, edited by Nasser Kehtarnavaz and Matthias F. Carlsohn. SPIE, 2019. http://dx.doi.org/10.1117/12.2519546.
Full text
9
Liu, Zihan, Genta Indra Winata, Andrea Madotto, and Pascale Fung. "Preserving Cross-Linguality of Pre-trained Models via Continual Learning." In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021). Stroudsburg, PA, USA: Association for Computational Linguistics, 2021. http://dx.doi.org/10.18653/v1/2021.repl4nlp-1.8.
Full text
10
Ostellino, S., A. Benso, and G. Politano. "Brain MRI Images Pre-processing of Heterogeneous Data-sets for Deep Learning Applications." In 13th International Conference on Bioinformatics Models, Methods and Algorithms. SCITEPRESS - Science and Technology Publications, 2022. http://dx.doi.org/10.5220/0010828500003123.
Full textReports on the topic "Learning with pre-built models"
1
Lasko, Kristofer, and Elena Sava. Semi-automated land cover mapping using an ensemble of support vector machines with moderate resolution imagery integrated into a custom decision support tool. Engineer Research and Development Center (U.S.), November 2021. http://dx.doi.org/10.21079/11681/42402.
Full textAbstract:
Land cover type is a fundamental remote sensing-derived variable for terrain analysis and environmental mapping applications. The currently available products are produced only for a single season or a specific year. Some of these products have a coarse resolution and quickly become outdated, as land cover type can undergo significant change over a short time period. In order to enable on-demand generation of timely and accurate land cover type products, we developed a sensor-agnostic framework leveraging pre-trained machine learning models. We also generated land cover models for Sentinel-2 (20m) and Landsat 8 imagery (30m) using either a single date of imagery or two dates of imagery for mapping land cover type. The two-date model includes 11 land cover type classes, whereas the single-date model contains 6 classes. The models’ overall accuracies were 84% (Sentinel-2 single date), 82% (Sentinel-2 two date), and 86% (Landsat 8 two date) across the continental United States. The three different models were built into an ArcGIS Pro Python toolbox to enable a semi-automated workflow for end users to generate their own land cover type maps on demand. The toolboxes were built using parallel processing and image-splitting techniques to enable faster computation and for use on less-powerful machines.
2
Cordero, Eugene, and Kiana Luong. Promoting Interest in Transportation Careers Among Young Women. Mineta Transportation Institute, November 2021. http://dx.doi.org/10.31979/mti.2021.2028.
Full textAbstract:
Transportation remains the largest source of U.S.-based carbon emissions, and reducing emissions from this source continues to challenge experts. Addressing challenging problems requires diverse modes of thinking—and at present the transportation workforce is not diverse in terms of gender, with women occupying only about 14% of the transportation workforce. This research developed and tested a school-based intervention that uses pro-environmental framing and exposure to women transportation role models to help attract more women to transportation careers. To investigate the efficacy of the intervention, the research team studied control and treatment groups of university students using pre- and post-surveys to measure changes in student understanding and interest in transportation fields and careers. Students in both groups were enrolled in a climate change course, and students in the treatment group completed an additional transportation learning module designed to stimulate interest in transportation careers. The results showed that by the end of the semester, student awareness that the transportation industry can provide green and sustainable careers increased by 39.7% in the treatment group compared to no change in the control group. In addition, student openness to working in a transportation related career increased by 17.5% for females in the treatment group compared to no change in the male treatment group and no change in the control group. Given the success of this intervention, similar educational modules at various educational levels could increase the number of women working in transportation. Should such approaches be successful, society will be better prepared to respond to environmental challenges like climate change.
3
Perdigão, Rui A. P. Information physics and quantum space technologies for natural hazard sensing, modelling and prediction. Meteoceanics, September 2021. http://dx.doi.org/10.46337/210930.
Full textAbstract:
Disruptive socio-natural transformations and climatic change, where system invariants and symmetries break down, defy the traditional complexity paradigms such as machine learning and artificial intelligence. In order to overcome this, we introduced non-ergodic Information Physics, bringing physical meaning to inferential metrics, and a coevolving flexibility to the metrics of information transfer, resulting in new methods for causal discovery and attribution. With this in hand, we develop novel dynamic models and analysis algorithms natively built for quantum information technological platforms, expediting complex system computations and rigour. Moreover, we introduce novel quantum sensing technologies in our Meteoceanics satellite constellation, providing unprecedented spatiotemporal coverage, resolution and lead, whilst using exclusively sustainable materials and processes across the value chain. Our technologies bring out novel information physical fingerprints of extreme events, with recently proven records in capturing early warning signs for extreme hydro-meteorologic events and seismic events, and do so with unprecedented quantum-grade resolution, robustness, security, speed and fidelity in sensing, processing and communication. Our advances, from Earth to Space, further provide crucial predictive edge and added value to early warning systems of natural hazards and long-term predictions supporting climatic security and action.
4
Filmer, Deon, James Habyarimana, and Shwetlena Sabarwal. Teacher Performance-Based Incentives and Learning Inequality. Research on Improving Systems of Education (RISE), September 2020. http://dx.doi.org/10.35489/bsg-rise-wp_2020/047.
Full textAbstract:
This study evaluates the impacts of low-cost, performance-based incentives in Tanzanian secondary schools. Results from a two-phase randomized trial show that incentives for teachers led to modest average improvements in student achievement across different subjects. Further, withdrawing incentives did not lead to a “discouragement effect” (once incentives were withdrawn, student performance did not fall below pre-baseline levels). Rather, impacts on learning were sustained beyond the intervention period. However, these incentives may have exacerbated learning inequality within and across schools. Increases in learning were concentrated among initially better-performing schools and students. At the same time, learning outcomes may have decreased for schools and students that were lower performing at baseline. Finally, the study finds that incentivizing students without simultaneously incentivizing teachers did not produce observable learning gains.
5
Tayeb, Shahab. Taming the Data in the Internet of Vehicles. Mineta Transportation Institute, January 2022. http://dx.doi.org/10.31979/mti.2022.2014.
Full textAbstract:
As an emerging field, the Internet of Vehicles (IoV) has a myriad of security vulnerabilities that must be addressed to protect system integrity. To stay ahead of novel attacks, cybersecurity professionals are developing new software and systems using machine learning techniques. Neural network architectures improve such systems, including Intrusion Detection System (IDSs), by implementing anomaly detection, which differentiates benign data packets from malicious ones. For an IDS to best predict anomalies, the model is trained on data that is typically pre-processed through normalization and feature selection/reduction. These pre-processing techniques play an important role in training a neural network to optimize its performance. This research studies the impact of applying normalization techniques as a pre-processing step to learning, as used by the IDSs. The impacts of pre-processing techniques play an important role in training neural networks to optimize its performance. This report proposes a Deep Neural Network (DNN) model with two hidden layers for IDS architecture and compares two commonly used normalization pre-processing techniques. Our findings are evaluated using accuracy, Area Under Curve (AUC), Receiver Operator Characteristic (ROC), F-1 Score, and loss. The experimentations demonstrate that Z-Score outperforms no-normalization and the use of Min-Max normalization.
6
Strutynska, Oksana V., Grygoriy M. Torbin, Mariia A. Umryk, and Roman M. Vernydub. Digitalization of the educational process for the training of the pre-service teachers. [б. в.], June 2021. http://dx.doi.org/10.31812/123456789/4437.
Full textAbstract:
According to the Development Concept of the Digital Economy and Society in Ukraine, the priority of this area is to develop a substantial national policy on digitalization of education, as this is the key part of the education reform in Ukraine. For this reason, universities should firstly take into account the particularities of teaching the current generation of students and the needs of the digital society as a whole. This paper considers the process of transition from informatization to digitalization in society, implementation of digital support for the educational process in the university, development of the digital educational environment for the training university teachers, and proposes the digital tools for such an environment. The authors propose several ways to improve the development level of digitalization of the educational environment in the university. This is to take into account the needs of the digital society and the modern generation of students, provide a high level of the digital literacy formation of university graduates and support the development of a new digital security system of the modern university. Aiming to design the digital educational environment for increasing the of educators’ digital literacy level, the authors propose to develop and implement the following computer, multimedia and computer-based learning tools and equipment, which includes blended and distance learning classes, cloud technologies, tools of virtual and augmented reality, tools for gamification of the educational process, educational robotics, tools for learning 3D technologies, MOOCs.
7
Kriegel, Francesco. Learning description logic axioms from discrete probability distributions over description graphs (Extended Version). Technische Universität Dresden, 2018. http://dx.doi.org/10.25368/2022.247.
Full textAbstract:
Description logics in their standard setting only allow for representing and reasoning with crisp knowledge without any degree of uncertainty. Of course, this is a serious shortcoming for use cases where it is impossible to perfectly determine the truth of a statement. For resolving this expressivity restriction, probabilistic variants of description logics have been introduced. Their model-theoretic semantics is built upon so-called probabilistic interpretations, that is, families of directed graphs the vertices and edges of which are labeled and for which there exists a probability measure on this graph family. Results of scientific experiments, e.g., in medicine, psychology, or biology, that are repeated several times can induce probabilistic interpretations in a natural way. In this document, we shall develop a suitable axiomatization technique for deducing terminological knowledge from the assertional data given in such probabilistic interpretations. More specifically, we consider a probabilistic variant of the description logic EL⊥, and provide a method for constructing a set of rules, so-called concept inclusions, from probabilistic interpretations in a sound and complete manner.
8
Velychko, Vladyslav Ye, Elena H. Fedorenko, and Darja A. Kassim. Conceptual Bases of Use of Free Software in the Professional Training of Pre-Service Teacher of Mathematics, Physics and Computer Science. [б. в.], November 2018. http://dx.doi.org/10.31812/123456789/2667.
Full textAbstract:
The development of education is associated primarily with the use of ICT. A significant experience is already gained in how to use educational computer systems while new forms and methods of learning based on modern information technology are being developed and used. In relation to free software, a period when the quantity should translate into quality and an indicator of such translation is development of the concept of the introduction of free software in educational activities of universities. The proposed concept, let’s take Ukraine as an example, determines the main aim of introduction of free software in the training of pre-service of Mathematics, Physics and Computer Science; defines the objectives, measures, principles, the role and value of free software in the informatization process and results of its implementation.
9
Kharkivska, Alla A., Liudmyla V. Shtefan, Muntasir Alsadoon, and Aleksandr D. Uchitel. Technology of forming future journalists' social information competence in Iraq based on the use of a dynamic pedagogical site. [б. в.], July 2020. http://dx.doi.org/10.31812/123456789/3853.
Full textAbstract:
The article reveals scientific approaches to substantiating and developing technology to form social information competence of future Iraqi journalists based on using a dynamic pedagogical site. After pre-interviewing students of the Journalism Faculty at Al-Imam Al-Kadhim University College for Islamic Sciences in Baghdad, the authors came to the conclusion there are issues on defining the essence of social information competences. It is established that the majority of respondents do not feel satisfied with the conditions for forming these competences in the education institutions. At the same time, there were also positive trends as most future journalists recognized the importance of these professional competences for their professional development and had a desire to attend additional courses, including distance learning ones. Subsequently, the authors focused on social information competence of future journalists, which is a key issue according to European requirements. The authors describe the essence of this competence as an integrative quality of personality, which characterizes an ability to select, transform information and allows to organize effective professional communication on the basis of the use of modern communicative technologies in the process of individual or team work. Based on the analysis of literary sources, its components are determined: motivational, cognitive, operational and personal. The researchers came to the conclusion that it is necessary to develop a technology for forming social information competence of future journalists based on the use of modern information technologies. The necessity of technology implementation through the preparatory, motivational, operational and diagnostic correction stages was substantiated and its model was developed. The authors found that the main means of technology implementation should be a dynamic pedagogical site, which, unlike static, allows to expand technical possibilities by using such applications as photo galleries, RSS modules, forums, etc. Technically, it can be created using Site builder. Further research will be aimed at improving the structure of the dynamic pedagogical site of the developed technology.
10
Tyshchenko, Yelyzaveta Yu, and Andrii M. Striuk. Актуальність розробки моделі адаптивного навчання. [б. в.], December 2018. http://dx.doi.org/10.31812/123456789/2889.
Full textAbstract:
The learning process can be made most effective by transferring the educational process to the electronic environment. Thanks to adaptive testing, the accuracy, quality, reliability of training and student interest are enhanced, which allows him to be more motivated. This is a new approach for the student to master most of the information. The introduction of an adaptive testing system ensures the improvement of student learning performance. From the proper organization of the control of knowledge depends on the effectiveness of the educational process. Adaptive testing involves changing the sequence of tasks in the testing process itself, taking into account the answers to the tasks already received. In the process of passing the test, a personality model is built that learns for later use in selecting the following testing tasks, depending on the level of knowledge of the student and his individual characteristics. When calculating the assessment, the adaptive testing system takes into account the probability that the student can guess the answer, the number of attempts to pass the test and the average result achieved during all attempts. The complex of tasks for adaptive testing can be developed taking into account a separate type of perception of information by each student, that is, the student is offered tasks that he is able to cope with and which are interesting for him, which means he is more confident in his abilities and aims at successful completion of the course.