Articles de revues sur le sujet « Generative classifiers »
Pour voir les autres types de publications sur ce sujet consultez le lien suivant : Generative classifiers.
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleurs articles de revues pour votre recherche sur le sujet « Generative classifiers ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les articles de revues sur diverses disciplines et organisez correctement votre bibliographie.
1
Varga, Michal, Ján Jadlovský et Slávka Jadlovská. « Generative Enhancement of 3D Image Classifiers ». Applied Sciences 10, no 21 (22 octobre 2020) : 7433. http://dx.doi.org/10.3390/app10217433.
Texte intégralRésumé :
In this paper, we propose a methodology for generative enhancement of existing 3D image classifiers. This methodology is based on combining the advantages of both non-generative classifiers and generative modeling. Its purpose is to streamline the synthesis of novel deep neural networks by embedding existing compatible classifiers into a generative network architecture. A demonstration of this process and evaluation of its effectiveness is performed using a 3D convolutional classifier and its generative equivalent—a 3D conditional generative adversarial network classifier. The results of the experiments show that the generative classifier delivers higher performance, gaining a relative classification accuracy improvement of 7.43%. An increase of accuracy is also observed when comparing it to a plain convolutional classifier that was trained on a dataset augmented with samples created by the trained generator. This suggests a desirable knowledge sharing mechanism exists within the hybrid discriminator-classifier network.
2
Shakhuro, V. I., et A. S. Konushin. « IMAGE SYNTHESIS WITH NEURAL NETWORKS FOR TRAFFIC SIGN CLASSIFICATION ». Computer Optics 42, no 1 (30 mars 2018) : 105–12. http://dx.doi.org/10.18287/2412-6179-2018-42-1-105-112.
Texte intégralRésumé :
In this work, we research the applicability of generative adversarial neural networks for generating training samples for a traffic sign classification task. We consider generative neural networks trained using the Wasserstein metric. As a baseline method for comparison, we take image generation based on traffic sign icons. Experimental evaluation of the classifiers based on convolutional neural networks is conducted on real data, two types of synthetic data, and a combination of real and synthetic data. The experiments show that modern generative neural networks are capable of generating realistic training samples for traffic sign classification that outperform methods for generating images with icons, but are still slightly worse than real images for classifier training.
3
Sensoy, Murat, Lance Kaplan, Federico Cerutti et Maryam Saleki. « Uncertainty-Aware Deep Classifiers Using Generative Models ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 04 (3 avril 2020) : 5620–27. http://dx.doi.org/10.1609/aaai.v34i04.6015.
Texte intégralRésumé :
Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution. These approaches use an auxiliary data set during training to represent out-of-distribution samples. However, selection or creation of such an auxiliary data set is non-trivial, especially for high dimensional data such as images. In this work we develop a novel neural network model that is able to express both aleatoric and epistemic uncertainty to distinguish decision boundary and out-of-distribution regions of the feature space. To this end, variational autoencoders and generative adversarial networks are incorporated to automatically generate out-of-distribution exemplars for training. Through extensive analysis, we demonstrate that the proposed approach provides better estimates of uncertainty for in- and out-of-distribution samples, and adversarial examples on well-known data sets against state-of-the-art approaches including recent Bayesian approaches for neural networks and anomaly detection methods.
4
Yakura, Hiromu, Youhei Akimoto et Jun Sakuma. « Generate (Non-Software) Bugs to Fool Classifiers ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 01 (3 avril 2020) : 1070–78. http://dx.doi.org/10.1609/aaai.v34i01.5457.
Texte intégralRésumé :
In adversarial attacks intended to confound deep learning models, most studies have focused on limiting the magnitude of the modification so that humans do not notice the attack. On the other hand, during an attack against autonomous cars, for example, most drivers would not find it strange if a small insect image were placed on a stop sign, or they may overlook it. In this paper, we present a systematic approach to generate natural adversarial examples against classification models by employing such natural-appearing perturbations that imitate a certain object or signal. We first show the feasibility of this approach in an attack against an image classifier by employing generative adversarial networks that produce image patches that have the appearance of a natural object to fool the target model. We also introduce an algorithm to optimize placement of the perturbation in accordance with the input image, which makes the generation of adversarial examples fast and likely to succeed. Moreover, we experimentally show that the proposed approach can be extended to the audio domain, for example, to generate perturbations that sound like the chirping of birds to fool a speech classifier.
5
Hassan, Anthony Rotimi, Rasaki Olawale Olanrewaju, Queensley C. Chukwudum, Sodiq Adejare Olanrewaju et S. E. Fadugba. « Comparison Study of Generative and Discriminative Models for Classification of Classifiers ». International Journal of Mathematics and Computers in Simulation 16 (28 juin 2022) : 76–87. http://dx.doi.org/10.46300/9102.2022.16.12.
Texte intégralRésumé :
In classification of classifier analysis, researchers have been worried about the classifier of existing generative and discriminative models in practice for analyzing attributes data. This makes it necessary to give an in-depth, systematic, interrelated, interconnected, and classification of classifier of generative and discriminative models. Generative models of Logistic and Multinomial Logistic regression models and discriminative models of Linear Discriminant Analysis (LDA) (for attribute P=1 and P>1), Quadratic Discriminant Analysis (QDA) and Naïve Bayes were thoroughly dealt with analytically and mathematically. A step-by-step empirical analysis of the mentioned models were carried-out via chemical analysis of wines grown in a region in Italy that was derived from three different cultivars (The three types of wines that constituted the three different cultivars or three classifiers). Naïve Bayes Classifier set the pace via leading a-prior probabilities.
6
Chen, Wei, Xinmiao Chen et Xiao Sun. « Emotional dialog generation via multiple classifiers based on a generative adversarial network ». Virtual Reality & ; Intelligent Hardware 3, no 1 (février 2021) : 18–32. http://dx.doi.org/10.1016/j.vrih.2020.12.001.
Texte intégral
7
Lu, Zhengdong, Todd K. Leen et Jeffrey Kaye. « Kernels for Longitudinal Data with Variable Sequence Length and Sampling Intervals ». Neural Computation 23, no 9 (septembre 2011) : 2390–420. http://dx.doi.org/10.1162/neco_a_00164.
Texte intégralRésumé :
We develop several kernel methods for classification of longitudinal data and apply them to detect cognitive decline in the elderly. We first develop mixed-effects models, a type of hierarchical empirical Bayes generative models, for the time series. After demonstrating their utility in likelihood ratio classifiers (and the improvement over standard regression models for such classifiers), we develop novel Fisher kernels based on mixture of mixed-effects models and use them in support vector machine classifiers. The hierarchical generative model allows us to handle variations in sequence length and sampling interval gracefully. We also give nonparametric kernels not based on generative models, but rather on the reproducing kernel Hilbert space. We apply the methods to detecting cognitive decline from longitudinal clinical data on motor and neuropsychological tests. The likelihood ratio classifiers based on the neuropsychological tests perform better than than classifiers based on the motor behavior. Discriminant classifiers performed better than likelihood ratio classifiers for the motor behavior tests.
8
Amiryousefi, Ali, Ville Kinnula et Jing Tang. « Bayes in Wonderland ! Predictive Supervised Classification Inference Hits Unpredictability ». Mathematics 10, no 5 (5 mars 2022) : 828. http://dx.doi.org/10.3390/math10050828.
Texte intégralRésumé :
The marginal Bayesian predictive classifiers (mBpc), as opposed to the simultaneous Bayesian predictive classifiers (sBpc), handle each data separately and, hence, tacitly assume the independence of the observations. Due to saturation in learning of generative model parameters, the adverse effect of this false assumption on the accuracy of mBpc tends to wear out in the face of an increasing amount of training data, guaranteeing the convergence of these two classifiers under the de Finetti type of exchangeability. This result, however, is far from trivial for the sequences generated under Partition Exchangeability (PE), where even umpteen amount of training data does not rule out the possibility of an unobserved outcome (Wonderland!). We provide a computational scheme that allows the generation of the sequences under PE. Based on that, with controlled increase of the training data, we show the convergence of the sBpc and mBpc. This underlies the use of simpler yet computationally more efficient marginal classifiers instead of simultaneous. We also provide a parameter estimation of the generative model giving rise to the partition exchangeable sequence as well as a testing paradigm for the equality of this parameter across different samples. The package for Bayesian predictive supervised classifications, parameter estimation and hypothesis testing of the Ewens sampling formula generative model is deposited on CRAN as PEkit package.
9
Elzobi, Moftah, et Ayoub Al-Hamadi. « Generative vs. Discriminative Recognition Models for Off-Line Arabic Handwriting ». Sensors 18, no 9 (24 août 2018) : 2786. http://dx.doi.org/10.3390/s18092786.
Texte intégralRésumé :
The majority of handwritten word recognition strategies are constructed on learning-based generative frameworks from letter or word training samples. Theoretically, constructing recognition models through discriminative learning should be the more effective alternative. The primary goal of this research is to compare the performances of discriminative and generative recognition strategies, which are described by generatively-trained hidden Markov modeling (HMM), discriminatively-trained conditional random fields (CRF) and discriminatively-trained hidden-state CRF (HCRF). With learning samples obtained from two dissimilar databases, we initially trained and applied an HMM classification scheme. To enable HMM classifiers to effectively reject incorrect and out-of-vocabulary segmentation, we enhance the models with adaptive threshold schemes. Aside from proposing such schemes for HMM classifiers, this research introduces CRF and HCRF classifiers in the recognition of offline Arabic handwritten words. Furthermore, the efficiencies of all three strategies are fully assessed using two dissimilar databases. Recognition outcomes for both words and letters are presented, with the pros and cons of each strategy emphasized.
10
Karaliutė, Marta, et Kęstutis Dučinskas. « Performance of the supervised generative classifiers of spatio-temporal areal data using various spatial autocorrelation indexes ». Nonlinear Analysis : Modelling and Control 28 (22 février 2023) : 1–14. http://dx.doi.org/10.15388/namc.2023.28.31434.
Texte intégralRésumé :
This article is concerned with a generative approach to supervised classification of spatio-temporal data collected at fixed areal units and modeled by Gaussian Markov random field. We focused on the classifiers based on Bayes discriminant functions formed by the log-ratio of the class conditional likelihoods. As a novel modeling contribution, we propose to use decision threshold values induced by three popular spatial autocorrelation indexes, i.e., Moran’s I, Geary’s C and Getis–Ord G. The goal of this study is to extend the recent investigations in the context of geostatistical and hidden Markov Gaussian models to one in the context of areal Gaussian Markov models. The classifiers performance measures are chosen to be the average accuracy rate, which shows the percentage of correctly classified test data, balanced accuracy rate specified by the average of sensitivity and specificity and the geometric mean of sensitivity and specificity. The proposed methodology is illustrated using annual death rate data collected by the Institute of Hygiene of the Republic of Lithuania from the 60 unicipalities in the period from 2001 to 2019. Classification model selection procedure is illustrated on three data sets with class labels specified by the threshold to mortality index due to acute cardiovascular event, malignant neoplasms and diseases of the circulatory system. Presented critical comparison among proposed approach classifiers with various spatial autocorrelation indexes (decision threshold values) and classifier based hidden Markov model can aid in the selection of proper classification techniques for the spatio-temporal areal data.
11
Kumar Bhowmik, Tapan. « Naive Bayes vs Logistic Regression : Theory, Implementation and Experimental Validation ». Inteligencia Artificial 18, no 56 (18 décembre 2015) : 14. http://dx.doi.org/10.4114/intartif.vol18iss56pp14-30.
Texte intégralRésumé :
This article presents the theoretical derivation as well as practical steps for implementing Naive Bayes (NB) and Logistic Regression (LR) classifiers. A generative learning under Gaussian Naive Bayes assumption and two discriminative learning techniques based on gradient ascent and Newton-Raphson methods are described to estimate the parameters of LR. Some limitation of learning techniques and implementation issues are discussed as well. A set of experiments are performed for both the classifiers under different learning circumstances and their performances are compared. From the experiments, it is observed that LR learning with gradient ascent technique outperforms general NB classifier. However, under Gaussian Naive Bayes assumption, both classifiers NB and LR perform similar.
12
Perina, Alessandro, Marco Cristani, Umberto Castellani, Vittorio Murino et Nebojsa Jojic. « Free Energy Score Spaces : Using Generative Information in Discriminative Classifiers ». IEEE Transactions on Pattern Analysis and Machine Intelligence 34, no 7 (juillet 2012) : 1249–62. http://dx.doi.org/10.1109/tpami.2011.241.
Texte intégral
13
Fisch, Dominik, Edgar Kalkowski et Bernhard Sick. « Knowledge Fusion for Probabilistic Generative Classifiers with Data Mining Applications ». IEEE Transactions on Knowledge and Data Engineering 26, no 3 (mars 2014) : 652–66. http://dx.doi.org/10.1109/tkde.2013.20.
Texte intégral
14
Simon, Judy. « Image Augmentation based on GAN deep learning approach with Textual Content Descriptors ». September 2021 3, no 3 (1 novembre 2021) : 210–25. http://dx.doi.org/10.36548/jitdw.2021.3.005.
Texte intégralRésumé :
Computer vision, also known as computational visual perception, is a branch of artificial intelligence that allows computers to interpret digital pictures and videos in a manner comparable to biological vision. It entails the development of techniques for simulating biological vision. The aim of computer vision is to extract more meaningful information from visual input than that of a biological vision. Computer vision is exploding due to the avalanche of data being produced today. Powerful generative models, such as Generative Adversarial Networks (GANs), are responsible for significant advances in the field of picture creation. The focus of this research is to concentrate on textual content descriptors in the images used by GANs to generate synthetic data from the MNIST dataset to either supplement or replace the original data while training classifiers. This can provide better performance than other traditional image enlarging procedures due to the good handling of synthetic data. It shows that training classifiers on synthetic data are as effective as training them on pure data alone, and it also reveals that, for small training data sets, supplementing the dataset by first training GANs on the data may lead to a significant increase in classifier performance.
15
Epshteyn, A., et G. DeJong. « Generative Prior Knowledge for Discriminative Classification ». Journal of Artificial Intelligence Research 27 (25 septembre 2006) : 25–53. http://dx.doi.org/10.1613/jair.1934.
Texte intégralRésumé :
We present a novel framework for integrating prior knowledge into discriminative classifiers. Our framework allows discriminative classifiers such as Support Vector Machines (SVMs) to utilize prior knowledge specified in the generative setting. The dual objective of fitting the data and respecting prior knowledge is formulated as a bilevel program, which is solved (approximately) via iterative application of second-order cone programming. To test our approach, we consider the problem of using WordNet (a semantic database of English language) to improve low-sample classification accuracy of newsgroup categorization. WordNet is viewed as an approximate, but readily available source of background knowledge, and our framework is capable of utilizing it in a flexible way.
16
Wang, Liwei, Xiong Li, Zhuowen Tu et Jiaya Jia. « Discriminative Clustering via Generative Feature Mapping ». Proceedings of the AAAI Conference on Artificial Intelligence 26, no 1 (20 septembre 2021) : 1162–68. http://dx.doi.org/10.1609/aaai.v26i1.8305.
Texte intégralRésumé :
Existing clustering methods can be roughly classified into two categories: generative and discriminative approaches. Generative clustering aims to explain the data and thus is adaptive to the underlying data distribution; discriminative clustering, on the other hand, emphasizes on finding partition boundaries. In this paper, we take the advantages of both models by coupling the two paradigms through feature mapping derived from linearizing Bayesian classifiers. Such the feature mapping strategy maps nonlinear boundaries of generative clustering to linear ones in the feature space where we explicitly impose the maximum entropy principle. We also propose the unified probabilistic framework, enabling solvers using standard techniques. Experiments on a variety of datasets bear out the notable benefit of our method in terms of adaptiveness and robustness.
17
Montero, Alberto, Elisenda Bonet-Carne et Xavier Paolo Burgos-Artizzu. « Generative Adversarial Networks to Improve Fetal Brain Fine-Grained Plane Classification ». Sensors 21, no 23 (29 novembre 2021) : 7975. http://dx.doi.org/10.3390/s21237975.
Texte intégralRésumé :
Generative adversarial networks (GANs) have been recently applied to medical imaging on different modalities (MRI, CT, X-ray, etc). However there are not many applications on ultrasound modality as a data augmentation technique applied to downstream classification tasks. This study aims to explore and evaluate the generation of synthetic ultrasound fetal brain images via GANs and apply them to improve fetal brain ultrasound plane classification. State of the art GANs stylegan2-ada were applied to fetal brain image generation and GAN-based data augmentation classifiers were compared with baseline classifiers. Our experimental results show that using data generated by both GANs and classical augmentation strategies allows for increasing the accuracy and area under the curve score.
18
Abedi, Masoud, Lars Hempel, Sina Sadeghi et Toralf Kirsten. « GAN-Based Approaches for Generating Structured Data in the Medical Domain ». Applied Sciences 12, no 14 (13 juillet 2022) : 7075. http://dx.doi.org/10.3390/app12147075.
Texte intégralRésumé :
Modern machine and deep learning methods require large datasets to achieve reliable and robust results. This requirement is often difficult to meet in the medical field, due to data sharing limitations imposed by privacy regulations or the presence of a small number of patients (e.g., rare diseases). To address this data scarcity and to improve the situation, novel generative models such as Generative Adversarial Networks (GANs) have been widely used to generate synthetic data that mimic real data by representing features that reflect health-related information without reference to real patients. In this paper, we consider several GAN models to generate synthetic data used for training binary (malignant/benign) classifiers, and compare their performances in terms of classification accuracy with cases where only real data are considered. We aim to investigate how synthetic data can improve classification accuracy, especially when a small amount of data is available. To this end, we have developed and implemented an evaluation framework where binary classifiers are trained on extended datasets containing both real and synthetic data. The results show improved accuracy for classifiers trained with generated data from more advanced GAN models, even when limited amounts of original data are available.
19
Fisch, Dominik, Christian Gruhl, Edgar Kalkowski, Bernhard Sick et Seppo J. Ovaska. « Towards automation of knowledge understanding : An approach for probabilistic generative classifiers ». Information Sciences 370-371 (novembre 2016) : 476–96. http://dx.doi.org/10.1016/j.ins.2016.08.016.
Texte intégral
20
Li, Yuanzhang, Yaxiao Wang, Ye Wang, Lishan Ke et Yu-an Tan. « A feature-vector generative adversarial network for evading PDF malware classifiers ». Information Sciences 523 (juin 2020) : 38–48. http://dx.doi.org/10.1016/j.ins.2020.02.075.
Texte intégral
21
Wang, Tianshi, Li Liu, Huaxiang Zhang, Long Zhang et Xiuxiu Chen. « Joint Character-Level Convolutional and Generative Adversarial Networks for Text Classification ». Complexity 2020 (30 avril 2020) : 1–11. http://dx.doi.org/10.1155/2020/8516216.
Texte intégralRésumé :
With the continuous renewal of text classification rules, text classifiers need more powerful generalization ability to process the datasets with new text categories or small training samples. In this paper, we propose a text classification framework under insufficient training sample conditions. In the framework, we first quantify the texts by a character-level convolutional neural network and input the textual features into an adversarial network and a classifier, respectively. Then, we use the real textual features to train a generator and a discriminator so as to make the distribution of generated data consistent with that of real data. Finally, the classifier is cooperatively trained by real data and generated data. Extensive experimental validation on four public datasets demonstrates that our method significantly performs better than the comparative methods.
22
Sandouka, Soha B., Yakoub Bazi, Haikel Alhichri et Naif Alajlan. « Unified Generative Adversarial Networks for Multidomain Fingerprint Presentation Attack Detection ». Entropy 23, no 8 (21 août 2021) : 1089. http://dx.doi.org/10.3390/e23081089.
Texte intégralRésumé :
With the rapid growth of fingerprint-based biometric systems, it is essential to ensure the security and reliability of the deployed algorithms. Indeed, the security vulnerability of these systems has been widely recognized. Thus, it is critical to enhance the generalization ability of fingerprint presentation attack detection (PAD) cross-sensor and cross-material settings. In this work, we propose a novel solution for addressing the case of a single source domain (sensor) with large labeled real/fake fingerprint images and multiple target domains (sensors) with only few real images obtained from different sensors. Our aim is to build a model that leverages the limited sample issues in all target domains by transferring knowledge from the source domain. To this end, we train a unified generative adversarial network (UGAN) for multidomain conversion to learn several mappings between all domains. This allows us to generate additional synthetic images for the target domains from the source domain to reduce the distribution shift between fingerprint representations. Then, we train a scale compound network (EfficientNetV2) coupled with multiple head classifiers (one classifier for each domain) using the source domain and the translated images. The outputs of these classifiers are then aggregated using an additional fusion layer with learnable weights. In the experiments, we validate the proposed methodology on the public LivDet2015 dataset. The experimental results show that the proposed method improves the average classification accuracy over twelve classification scenarios from 67.80 to 80.44% after adaptation.
23
Subedi, Bharat, V. E. Sathishkumar, V. Maheshwari, M. Sandeep Kumar, Prabhu Jayagopal et Shaikh Muhammad Allayear. « Feature Learning-Based Generative Adversarial Network Data Augmentation for Class-Based Few-Shot Learning ». Mathematical Problems in Engineering 2022 (21 juillet 2022) : 1–20. http://dx.doi.org/10.1155/2022/9710667.
Texte intégralRésumé :
As training deep neural networks enough requires a large amount of data, there have been a lot of studies to deal with this problem. Data augmentation techniques are basic solutions to increase training data using existing data. Geometric transformations and color space augmentations are well-known augmentation techniques, but they still require some manual work and can generate limited types of data only. Therefore, there are many interests in generative-model-based augmentation lately, which can learn the distribution of data. This study proposes a set of GAN-based data augmentation methods that can generate good quality training data. The proposed networks, f-DAGAN (data augmentation generative adversarial networks), have been motivated by the DAGAN that learns data distribution from two real data. The basic f-DAGAN uses dual discriminators handling both generated data and generated feature spaces for better learning the given data. The other versions of f-DAGANs have been proposed for generating hard or easy data that have additional dual classifiers for both generated data and feature spaces to control the generator. Hard data is useful for optimized training to increase the target performance such as classification accuracy. Easy data generation can be used especially in few-shot learning. The quality of generated data has been validated in two ways: using t-SNE visualization of generated data and classification accuracy by training with generated data using the MNIST data set. The t-SNE representations show that data generated by f-DAGAN are evenly distributed for every class better than the exiting generative model-based augmentation methods. The f-DAGAN also shows the best classification accuracy by training with generated data. The f-DAGAN version for easy and hard data generation generates data well from five-shot learning and performs well in sample data generation experiments.
24
Liakos, Konstantinos G., Georgios K. Georgakilas, Fotis C. Plessas et Paris Kitsos. « GAINESIS : Generative Artificial Intelligence NEtlists SynthesIS ». Electronics 11, no 2 (13 janvier 2022) : 245. http://dx.doi.org/10.3390/electronics11020245.
Texte intégralRésumé :
A significant problem in the field of hardware security consists of hardware trojan (HT) viruses. The insertion of HTs into a circuit can be applied for each phase of the circuit chain of production. HTs degrade the infected circuit, destroy it or leak encrypted data. Nowadays, efforts are being made to address HTs through machine learning (ML) techniques, mainly for the gate-level netlist (GLN) phase, but there are some restrictions. Specifically, the number and variety of normal and infected circuits that exist through the free public libraries, such as Trust-HUB, are based on the few samples of benchmarks that have been created from circuits large in size. Thus, it is difficult, based on these data, to develop robust ML-based models against HTs. In this paper, we propose a new deep learning (DL) tool named Generative Artificial Intelligence Netlists SynthesIS (GAINESIS). GAINESIS is based on the Wasserstein Conditional Generative Adversarial Network (WCGAN) algorithm and area–power analysis features from the GLN phase and synthesizes new normal and infected circuit samples for this phase. Based on our GAINESIS tool, we synthesized new data sets, different in size, and developed and compared seven ML classifiers. The results demonstrate that our new generated data sets significantly enhance the performance of ML classifiers compared with the initial data set of Trust-HUB.
25
Levine, AB, J. Peng, SJM Jones, A. Bashashati et S. Yip. « Synthesis of glioma histopathology images using generative adversarial networks ». Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques 48, s1 (mai 2021) : S3. http://dx.doi.org/10.1017/cjn.2021.91.
Texte intégralRésumé :
Deep learning, a subset of artificial intelligence, has shown great potential in several recent applications to pathology. These have mainly involved the use of classifiers to diagnose disease, while generative modelling techniques have been less frequently used. Generative adversarial networks (GANs) are a type of deep learning model that has been used to synthesize realistic images in a range of domains, both general purpose and medical. In the GAN framework, a generator network is trained to synthesize fake images, while a dueling discriminator network aims to distinguish between the fake images and a set of real training images. As GAN training progresses, the generator network ideally learns the important features of a dataset, allowing it to create images that the discriminator cannot distinguish from the real ones. We report on our use of GANs to synthesize high resolution, realistic histopathology images of gliomas. The well- known Progressive GAN framework was trained on a set of image patches extracted from digital slides in the Cancer Genome Atlas repository, and was able to generate fake images that were visually indistinguishable from the real training images. Generative modelling in pathology has numerous potential applications, including dataset augmentation for training deep learning classifiers, image processing, and expanding educational material.LEARNING OBJECTIVESThis presentation will enable the learner to: 1.Explain basic principles of generative modelling in deep learning.2.Discuss applications of deep learning to neuropathology image synthesis.
26
Graña, Manuel, Leire Ozaeta et Darya Chyzhyk. « Resting State Effective Connectivity Allows Auditory Hallucination Discrimination ». International Journal of Neural Systems 27, no 05 (3 mai 2017) : 1750019. http://dx.doi.org/10.1142/s0129065717500198.
Texte intégralRésumé :
Hallucinations are elusive phenomena that have been associated with psychotic behavior, but that have a high prevalence in healthy population. Some generative mechanisms of Auditory Hallucinations (AH) have been proposed in the literature, but so far empirical evidence is scarce. The most widely accepted generative mechanism hypothesis nowadays consists in the faulty workings of a network of brain areas including the emotional control, the audio and language processing, and the inhibition and self-attribution of the signals in the auditive cortex. In this paper, we consider two methods to analyze resting state fMRI (rs-fMRI) data, in order to measure effective connections between the brain regions involved in the AH generation process. These measures are the Dynamic Causal Modeling (DCM) cross-covariance function (CCF) coefficients, and the partially directed coherence (PDC) coefficients derived from Granger Causality (GC) analysis. Effective connectivity measures are treated as input classifier features to assess their significance by means of cross-validation classification accuracy results in a wrapper feature selection approach. Experimental results using Support Vector Machine (SVM) classifiers on an rs-fMRI dataset of schizophrenia patients with and without a history of AH confirm that the main regions identified in the AH generative mechanism hypothesis have significant effective connection values, under both DCM and PDC evaluation.
27
Nan, Zhixiong, Yang Liu, Nanning Zheng et Song-Chun Zhu. « Recognizing Unseen Attribute-Object Pair with Generative Model ». Proceedings of the AAAI Conference on Artificial Intelligence 33 (17 juillet 2019) : 8811–18. http://dx.doi.org/10.1609/aaai.v33i01.33018811.
Texte intégralRésumé :
In this paper, we are studying the problem of recognizing attribute-object pairs that do not appear in the training dataset, which is called unseen attribute-object pair recognition. Existing methods mainly learn a discriminative classifier or compose multiple classifiers to tackle this problem, which exhibit poor performance for unseen pairs. The key reasons for this failure are 1) they have not learned an intrinsic attributeobject representation, and 2) the attribute and object are processed either separately or equally so that the inner relation between the attribute and object has not been explored. To explore the inner relation of attribute and object as well as the intrinsic attribute-object representation, we propose a generative model with the encoder-decoder mechanism that bridges visual and linguistic information in a unified end-to-end network. The encoder-decoder mechanism presents the impressive potential to find an intrinsic attribute-object feature representation. In addition, combining visual and linguistic features in a unified model allows to mine the relation of attribute and object. We conducted extensive experiments to compare our method with several state-of-the-art methods on two challenging datasets. The results show that our method outperforms all other methods.
28
Chen, Zhijun, Jingming Zhang, Yishi Zhang et Zihao Huang. « Traffic Accident Data Generation Based on Improved Generative Adversarial Networks ». Sensors 21, no 17 (27 août 2021) : 5767. http://dx.doi.org/10.3390/s21175767.
Texte intégralRésumé :
For urban traffic, traffic accidents are the most direct and serious risk to people’s lives, and rapid recognition and warning of traffic accidents is an important remedy to reduce their harmful effects. However, research scholars are often confronted with the problem of scarce and difficult-to-collect accident data resources for traffic accident scenarios. Therefore, in this paper, a traffic data generation model based on Generative Adversarial Networks (GAN) is developed. To make GAN applicable to non-graphical data, we improve the generator network structure of the model and used the generated model to resample the original data to obtain new traffic accident data. By constructing an adversarial neural network model, we generate a large number of data samples that are similar to the original traffic accident data. Results of the statistical test indicate that the generated samples are not significantly different from the original data. Furthermore, the experiments of traffic accident recognition with several representative classifiers demonstrate that the augmented data can effectively enhance the performance of accident recognition, with a maximum increase in accuracy of 3.05% and a maximum decrease in the false positive rate of 2.95%. Experimental results verify that the proposed method can provide reliable mass data support for the recognition of traffic accidents and road traffic safety.
29
Xu, Tingting, Ye Zhao et Xueliang Liu. « Dual Generative Network with Discriminative Information for Generalized Zero-Shot Learning ». Complexity 2021 (28 février 2021) : 1–11. http://dx.doi.org/10.1155/2021/6656797.
Texte intégralRésumé :
Zero-shot learning is dedicated to solving the classification problem of unseen categories, while generalized zero-shot learning aims to classify the samples selected from both seen classes and unseen classes, in which “seen” and “unseen” classes indicate whether they can be used in the training process, and if so, they indicate seen classes, and vice versa. Nowadays, with the promotion of deep learning technology, the performance of zero-shot learning has been greatly improved. Generalized zero-shot learning is a challenging topic that has promising prospects in many realistic scenarios. Although the zero-shot learning task has made gratifying progress, there is still a strong deviation between seen classes and unseen classes in the existing methods. Recent methods focus on learning a unified semantic-aligned visual representation to transfer knowledge between two domains, while ignoring the intrinsic characteristics of visual features which are discriminative enough to be classified by itself. To solve the above problems, we propose a novel model that uses the discriminative information of visual features to optimize the generative module, in which the generative module is a dual generation network framework composed of conditional VAE and improved WGAN. Specifically, the model uses the discrimination information of visual features, according to the relevant semantic embedding, synthesizes the visual features of unseen categories by using the learned generator, and then trains the final softmax classifier by using the generated visual features, thus realizing the recognition of unseen categories. In addition, this paper also analyzes the effect of the additional classifiers with different structures on the transmission of discriminative information. We have conducted a lot of experiments on six commonly used benchmark datasets (AWA1, AWA2, APY, FLO, SUN, and CUB). The experimental results show that our model outperforms several state-of-the-art methods for both traditional as well as generalized zero-shot learning.
30
Peppes, Nikolaos, Theodoros Alexakis, Evgenia Adamopoulou et Konstantinos Demestichas. « The Effectiveness of Zero-Day Attacks Data Samples Generated via GANs on Deep Learning Classifiers ». Sensors 23, no 2 (12 janvier 2023) : 900. http://dx.doi.org/10.3390/s23020900.
Texte intégralRésumé :
Digitization of most of the services that people use in their everyday life has, among others, led to increased needs for cybersecurity. As digital tools increase day by day and new software and hardware launch out-of-the box, detection of known existing vulnerabilities, or zero-day as they are commonly known, becomes one of the most challenging situations for cybersecurity experts. Zero-day vulnerabilities, which can be found in almost every new launched software and/or hardware, can be exploited instantly by malicious actors with different motives, posing threats for end-users. In this context, this study proposes and describes a holistic methodology starting from the generation of zero-day-type, yet realistic, data in tabular format and concluding to the evaluation of a Neural Network zero-day attacks’ detector which is trained with and without synthetic data. This methodology involves the design and employment of Generative Adversarial Networks (GANs) for synthetically generating a new and larger dataset of zero-day attacks data. The newly generated, by the Zero-Day GAN (ZDGAN), dataset is then used to train and evaluate a Neural Network classifier for zero-day attacks. The results show that the generation of zero-day attacks data in tabular format reaches an equilibrium after about 5000 iterations and produces data that are almost identical to the original data samples. Last but not least, it should be mentioned that the Neural Network model that was trained with the dataset containing the ZDGAN generated samples outperformed the same model when the later was trained with only the original dataset and achieved results of high validation accuracy and minimal validation loss.
31
Avdoshin, S. M., D. V. Pantiukhin, I. M. Voronkov, A. N. Nazarov, V. I. Muhamadiev, M. K. Gordenko, Nhich Van Dam et Ngoc Diep Nguyen. « Analysis of Neural Network Intrusion Detection Methods and Datasets for their Training ». Informacionnye Tehnologii 28, no 12 (14 décembre 2022) : 644–53. http://dx.doi.org/10.17587/it.28.644-653.
Texte intégralRésumé :
Approaches based on neural network classifiers to the detection of computer attacks are considered. The problems of training such classifiers are discussed. Data sets on computer attacks for wired and wireless systems are considered. The results of evaluating such sets by the degree of imbalance are given. The problems of learning on unbalanced data sets and approaches to balancing the training set in the case of rare attacks, including those using generative adversarial networks, are described.
32
Zhen, Hao, Yucheng Shi, Jidong J. Yang et Javad Mohammadpour Vehni. « Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification ». Applied Computing and Intelligence 3, no 1 (2022) : 13–26. http://dx.doi.org/10.3934/aci.2023002.
Texte intégralRésumé :
<abstract> <p>Classification using supervised learning requires annotating a large amount of classes-balanced data for model training and testing. This has practically limited the scope of applications with supervised learning, in particular deep learning. To address the issues associated with limited and imbalanced data, this paper introduces a sample-efficient co-supervised learning paradigm (SEC-CGAN), in which a conditional generative adversarial network (CGAN) is trained alongside the classifier and supplements semantics-conditioned, confidence-aware synthesized examples to the annotated data during the training process. In this setting, the CGAN not only serves as a <italic>co-supervisor</italic> but also provides complementary quality examples to aid the classifier training in an end-to-end fashion. Experiments demonstrate that the proposed SEC-CGAN outperforms the external classifier GAN (EC-GAN) and a baseline ResNet-18 classifier. For the comparison, all classifiers in above methods adopt the ResNet-18 architecture as the backbone. Particularly, for the Street View House Numbers dataset, using the 5% of training data, a test accuracy of 90.26% is achieved by SEC-CGAN as opposed to 88.59% by EC-GAN and 87.17% by the baseline classifier; for the highway image dataset, using the 10% of training data, a test accuracy of 98.27% is achieved by SEC-CGAN, compared to 97.84% by EC-GAN and 95.52% by the baseline classifier.</p> </abstract>
33
Lee, Jeongmin, Younkyoung Yoon et Junseok Kwon. « Generative Adversarial Network for Class-Conditional Data Augmentation ». Applied Sciences 10, no 23 (26 novembre 2020) : 8415. http://dx.doi.org/10.3390/app10238415.
Texte intégralRésumé :
We propose a novel generative adversarial network for class-conditional data augmentation (i.e., GANDA) to mitigate data imbalance problems in image classification tasks. The proposed GANDA generates minority class data by exploiting majority class information to enhance the classification accuracy of minority classes. For stable GAN training, we introduce a new denoising autoencoder initialization with explicit class conditioning in the latent space, which enables the generation of definite samples. The generated samples are visually realistic and have a high resolution. Experimental results demonstrate that the proposed GANDA can considerably improve classification accuracy, especially when datasets are highly imbalanced on standard benchmark datasets (i.e., MNIST and CelebA). Our generated samples can be easily used to train conventional classifiers to enhance their classification accuracy.
34
Faysal, Atik, Wai Keng Ngui, Meng Hee Lim et Mohd Salman Leong. « Noise Eliminated Ensemble Empirical Mode Decomposition Scalogram Analysis for Rotating Machinery Fault Diagnosis ». Sensors 21, no 23 (4 décembre 2021) : 8114. http://dx.doi.org/10.3390/s21238114.
Texte intégralRésumé :
Rotating machinery is one of the major components of industries that suffer from various faults due to the constant workload. Therefore, a fast and reliable fault diagnosis method is essential for machine condition monitoring. In this study, noise eliminated ensemble empirical mode decomposition (NEEEMD) was used for fault feature extraction. A convolution neural network (CNN) classifier was applied for classification because of its feature learning ability. A generalized CNN architecture was proposed to reduce the model training time. A sample size of 64×64×3 pixels RGB scalograms are used as the classifier input. However, CNN requires a large number of training data to achieve high accuracy and robustness. Deep convolution generative adversarial network (DCGAN) was applied for data augmentation during the training phase. To evaluate the effectiveness of the proposed feature extraction method, scalograms from related feature extraction methods such as ensemble empirical mode decomposition (EEMD), complementary EEMD (CEEMD), and continuous wavelet transform (CWT) are classified. The effectiveness of scalograms is also validated by comparing the classifier performance using grayscale samples from the raw vibration signals. All the outputs from bearing and blade fault classifiers showed that scalogram samples from the proposed NEEEMD method obtained the highest accuracy, sensitivity, and robustness using CNN. DCGAN was applied with the proposed NEEEMD scalograms to further increase the CNN classifier’s performance and identify the optimal number of training data. After training the classifier using augmented samples, the results showed that the classifier obtained even higher validation and test accuracy with greater robustness. The proposed method can be used as a more generalized and robust method for rotating machinery fault diagnosis.
35
La Salvia, Marco, Emanuele Torti, Raquel Leon, Himar Fabelo, Samuel Ortega, Beatriz Martinez-Vega, Gustavo M. Callico et Francesco Leporati. « Deep Convolutional Generative Adversarial Networks to Enhance Artificial Intelligence in Healthcare : A Skin Cancer Application ». Sensors 22, no 16 (17 août 2022) : 6145. http://dx.doi.org/10.3390/s22166145.
Texte intégralRésumé :
In recent years, researchers designed several artificial intelligence solutions for healthcare applications, which usually evolved into functional solutions for clinical practice. Furthermore, deep learning (DL) methods are well-suited to process the broad amounts of data acquired by wearable devices, smartphones, and other sensors employed in different medical domains. Conceived to serve the role of diagnostic tool and surgical guidance, hyperspectral images emerged as a non-contact, non-ionizing, and label-free technology. However, the lack of large datasets to efficiently train the models limits DL applications in the medical field. Hence, its usage with hyperspectral images is still at an early stage. We propose a deep convolutional generative adversarial network to generate synthetic hyperspectral images of epidermal lesions, targeting skin cancer diagnosis, and overcome small-sized datasets challenges to train DL architectures. Experimental results show the effectiveness of the proposed framework, capable of generating synthetic data to train DL classifiers.
36
Bhuvaneswari, M. « Gaussian mixture model : An application to parameter estimation and medical image classification ». Journal of Scientific and Innovative Research 5, no 3 (25 juin 2016) : 100–105. http://dx.doi.org/10.31254/jsir.2016.5308.
Texte intégralRésumé :
Gaussian mixture model based parameter estimation and classification has recently received great attention in modelling and processin g data. Gaussian Mixture Model (GMM) is the probabilistic model for representing the presence of subpopulations and it works well with the classification and parameter estimation strategy. Here in this work Maximum Likelihood Estimation (MLE) based on Expectation Maximization (EM) is being used for the parameter estimation approach and the estimated parameters are being used for the training and the testing of the images for their normality and the abnormality. With the mean and the covariance calculated as the parameters they are used in the Gaussian Mixture Model (GMM) based training of the classifier. Support Vector Machine a discriminative classifier and the Gaussian Mixture Model a generative model classifier are the two most popular techniques. The performance of the classification strategy of both the classifiers used has a better proficiency when compared to the other classifiers. By combining the SVM and GMM we co uld be able to classify at a better level since estimating the parameters through the GMM has a very few amount of features and hence it is not needed to use any of the feature reduction techniques. In this the GMM classifier and the SVM classifier are trained usin g the parameters and they are to be compared.
37
Shroff, Jugal, Rahee Walambe, Sunil Kumar Singh et Ketan Kotecha. « Enhanced Security Against Volumetric DDoS Attacks Using Adversarial Machine Learning ». Wireless Communications and Mobile Computing 2022 (11 mars 2022) : 1–10. http://dx.doi.org/10.1155/2022/5757164.
Texte intégralRésumé :
With the increasing number of Internet users, cybersecurity is becoming more and more critical. Denial of service (DoS) and distributed denial of service (DDoS) attacks are two of the most common types of attacks that can severely affect a website or a server and make them unavailable to other users. The number of DDoS attacks increased by 55% between the period January 2020 and March 2021. Some approaches for detecting the DoS and DDoS attacks employing different machine learning and deep learning techniques are reported in the literature. Recently, it is also observed that the attackers have started leveraging state-of-the-art AI tools such as generative models for generating synthetic attacks which fool the standard detectors. No concrete approach is reported for developing and training the models which are not only robust in the detection of standard DDoS attacks but which can also detect adversarial attacks which are created synthetically by the attackers with harmful intentions. To that end, in this work, we employ a generative adversarial network (GAN) to develop such a robust detector. The proposed framework can generate and classify the synthetic benign (normal) and malignant (DDoS) instances which are very similar to the corresponding real instances as evaluated by similarity scores. The GAN-based model also demonstrates how effectively the malicious actors can generate adversarial DDoS network traffic instances which look like normal instances using feature modification which are very difficult for the classifier to detect. An approach on how to make the classifiers robust enough to detect such kinds of deliberate adversarial attacks via modifying some specific attack features manually is also proposed. This work provides the first step towards developing a generic and robust detector for DDoS attacks originating from various sources.
38
Ostovan, Mahdi, Sadegh Samadi et Alireza Kazemi. « Generation of Human Micro-Doppler Signature Based on Layer-Reduced Deep Convolutional Generative Adversarial Network ». Computational Intelligence and Neuroscience 2022 (12 avril 2022) : 1–8. http://dx.doi.org/10.1155/2022/7365544.
Texte intégralRésumé :
Human activity recognition (HAR) using radar micro-Doppler has attracted the attention of researchers in the last decade. Using radar for human activity recognition has been very practical because of its unique advantages. There are several classifiers for the recognition of these activities, all of which require a rich database to produce fine output. Due to the limitations of providing and building a large database, radar micro-Doppler databases are usually limited in number. In this paper, a new method for the generation of radar micro-Doppler of the human body based on the deep convolutional generating adversarial network (DCGAN) is proposed. To generate the database, the required input is also generated by converting the existing motion database to simulated model-based radar data. The simulation results show the success of this method, even on a small amount of data.
39
Al-Qaderi, Mohammad, Elfituri Lahamer et Ahmad Rad. « A Two-Level Speaker Identification System via Fusion of Heterogeneous Classifiers and Complementary Feature Cooperation ». Sensors 21, no 15 (28 juillet 2021) : 5097. http://dx.doi.org/10.3390/s21155097.
Texte intégralRésumé :
We present a new architecture to address the challenges of speaker identification that arise in interaction of humans with social robots. Though deep learning systems have led to impressive performance in many speech applications, limited speech data at training stage and short utterances with background noise at test stage present challenges and are still open problems as no optimum solution has been reported to date. The proposed design employs a generative model namely the Gaussian mixture model (GMM) and a discriminative model—support vector machine (SVM) classifiers as well as prosodic features and short-term spectral features to concurrently classify a speaker’s gender and his/her identity. The proposed architecture works in a semi-sequential manner consisting of two stages: the first classifier exploits the prosodic features to determine the speaker’s gender which in turn is used with the short-term spectral features as inputs to the second classifier system in order to identify the speaker. The second classifier system employs two types of short-term spectral features; namely mel-frequency cepstral coefficients (MFCC) and gammatone frequency cepstral coefficients (GFCC) as well as gender information as inputs to two different classifiers (GMM and GMM supervector-based SVM) which in total leads to construction of four classifiers. The outputs from the second stage classifiers; namely GMM-MFCC maximum likelihood classifier (MLC), GMM-GFCC MLC, GMM-MFCC supervector SVM, and GMM-GFCC supervector SVM are fused at score level by the weighted Borda count approach. The weight factors are computed on the fly via Mamdani fuzzy inference system that its inputs are the signal to noise ratio and the length of utterance. Experimental evaluations suggest that the proposed architecture and the fusion framework are promising and can improve the recognition performance of the system in challenging environments where the signal-to-noise ratio is low, and the length of utterance is short; such scenarios often arise in social robot interactions with humans.
40
Andrade, Daniel, Akihiro Tamura et Masaaki Tsuchida. « Analysis of the Use of Background Distribution for Naive Bayes Classifiers ». Journal of Intelligent Systems 28, no 2 (24 avril 2019) : 259–73. http://dx.doi.org/10.1515/jisys-2017-0016.
Texte intégralRésumé :
Abstract The naive Bayes classifier is a popular classifier, as it is easy to train, requires no cross-validation for parameter tuning, and can be easily extended due to its generative model. Moreover, recently it was shown that the word probabilities (background distribution) estimated from large unlabeled corpora could be used to improve the parameter estimation of naive Bayes. However, previous methods do not explicitly allow to control how much the background distribution can influence the estimation of naive Bayes parameters. In contrast, we investigate an extension of the graphical model of naive Bayes such that a word is either generated from a background distribution or from a class-specific word distribution. We theoretically analyze this model and show the connection to Jelinek-Mercer smoothing. Experiments using four standard text classification data sets show that the proposed method can statistically significantly outperform previous methods that use the same background distribution.
41
Gangal, Varun, Abhinav Arora, Arash Einolghozati et Sonal Gupta. « Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection in Task Oriented Dialog ». Proceedings of the AAAI Conference on Artificial Intelligence 34, no 05 (3 avril 2020) : 7764–71. http://dx.doi.org/10.1609/aaai.v34i05.6280.
Texte intégralRésumé :
The task of identifying out-of-domain (OOD) input examples directly at test-time has seen renewed interest recently due to increased real world deployment of models. In this work, we focus on OOD detection for natural language sentence inputs to task-based dialog systems. Our findings are three-fold:First, we curate and release ROSTD (Real Out-of-Domain Sentences From Task-oriented Dialog) - a dataset of 4K OOD examples for the publicly available dataset from (Schuster et al. 2019). In contrast to existing settings which synthesize OOD examples by holding out a subset of classes, our examples were authored by annotators with apriori instructions to be out-of-domain with respect to the sentences in an existing dataset.Second, we explore likelihood ratio based approaches as an alternative to currently prevalent paradigms. Specifically, we reformulate and apply these approaches to natural language inputs. We find that they match or outperform the latter on all datasets, with larger improvements on non-artificial OOD benchmarks such as our dataset. Our ablations validate that specifically using likelihood ratios rather than plain likelihood is necessary to discriminate well between OOD and in-domain data.Third, we propose learning a generative classifier and computing a marginal likelihood (ratio) for OOD detection. This allows us to use a principled likelihood while at the same time exploiting training-time labels. We find that this approach outperforms both simple likelihood (ratio) based and other prior approaches. We are hitherto the first to investigate the use of generative classifiers for OOD detection at test-time.
42
Xue, Jing-Hao, et D. Michael Titterington. « Comment on “On Discriminative vs. Generative Classifiers : A Comparison of Logistic Regression and Naive Bayes” ». Neural Processing Letters 28, no 3 (26 octobre 2008) : 169–87. http://dx.doi.org/10.1007/s11063-008-9088-7.
Texte intégral
43
Wang, Guangxing, et Peng Ren. « Hyperspectral Image Classification with Feature-Oriented Adversarial Active Learning ». Remote Sensing 12, no 23 (26 novembre 2020) : 3879. http://dx.doi.org/10.3390/rs12233879.
Texte intégralRésumé :
Deep learning classifiers exhibit remarkable performance for hyperspectral image classification given sufficient labeled samples but show deficiency in the situation of learning with limited labeled samples. Active learning endows deep learning classifiers with the ability to alleviate this deficiency. However, existing active deep learning methods tend to underestimate the feature variability of hyperspectral images when querying informative unlabeled samples subject to certain acquisition heuristics. A major reason for this bias is that the acquisition heuristics are normally derived based on the output of a deep learning classifier, in which representational power is bounded by the number of labeled training samples at hand. To address this limitation, we developed a feature-oriented adversarial active learning (FAAL) strategy, which exploits the high-level features from one intermediate layer of a deep learning classifier for establishing an acquisition heuristic based on a generative adversarial network (GAN). Specifically, we developed a feature generator for generating fake high-level features and a feature discriminator for discriminating between the real high-level features and the fake ones. Trained with both the real and the fake high-level features, the feature discriminator comprehensively captures the feature variability of hyperspectral images and yields a powerful and generalized discriminative capability. We leverage the well-trained feature discriminator as the acquisition heuristic to measure the informativeness of unlabeled samples. Experimental results validate the effectiveness of both (i) the full FAAL framework and (ii) the adversarially learned acquisition heuristic, for the task of classifying hyperspectral images with limited labeled samples.
44
Kaiser, Christian, Matthias Schaufelberger, Reinald Peter Kühle, Andreas Wachter, Frederic Weichel, Niclas Hagen, Friedemann Ringwald et al. « Generative-Adversarial-Network-Based Data Augmentation for the Classification of Craniosynostosis ». Current Directions in Biomedical Engineering 8, no 2 (1 août 2022) : 17–20. http://dx.doi.org/10.1515/cdbme-2022-1005.
Texte intégralRésumé :
Abstract Craniosynostosis is a congenital disease characterized by the premature closure of one or multiple sutures of the infant’s skull. For diagnosis, 3D photogrammetric scans are a radiation-free alternative to computed tomography. However, data is only sparsely available and the role of data augmentation for the classification of craniosynostosis has not yet been analyzed. In this work, we use a 2D distance map representation of the infants’ heads with a convolutional-neural-network-based classifier and employ a generative adversarial network (GAN) for data augmentation. We simulate two data scarcity scenarios with 15% and 10% training data and test the influence of different degrees of added synthetic data and balancing underrepresented classes. We used total accuracy and F1-score as a metric to evaluate the final classifiers. For 15% training data, the GAN-augmented dataset showed an increased F1-score up to 0.1 and classification accuracy up to 3 %. For 10% training data, both metrics decreased. We present a deep convolutional GAN capable of creating synthetic data for the classification of craniosynostosis. Using a moderate amount of synthetic data using a GAN showed slightly better performance, but had little effect overall. The simulated scarcity scenario of 10% training data may have limited the model’s ability to learn the underlying data distribution.
45
Forster, Dennis, Abdul-Saboor Sheikh et Jörg Lücke. « Neural Simpletrons : Learning in the Limit of Few Labels with Directed Generative Networks ». Neural Computation 30, no 8 (août 2018) : 2113–74. http://dx.doi.org/10.1162/neco_a_01100.
Texte intégralRésumé :
We explore classifier training for data sets with very few labels. We investigate this task using a neural network for nonnegative data. The network is derived from a hierarchical normalized Poisson mixture model with one observed and two hidden layers. With the single objective of likelihood optimization, both labeled and unlabeled data are naturally incorporated into learning. The neural activation and learning equations resulting from our derivation are concise and local. As a consequence, the network can be scaled using standard deep learning tools for parallelized GPU implementation. Using standard benchmarks for nonnegative data, such as text document representations, MNIST, and NIST SD19, we study the classification performance when very few labels are used for training. In different settings, the network's performance is compared to standard and recently suggested semisupervised classifiers. While other recent approaches are more competitive for many labels or fully labeled data sets, we find that the network studied here can be applied to numbers of few labels where no other system has been reported to operate so far.
46
Cutellic, Pierre. « Towards encoding shape features with visual event-related potential based brain–computer interface for generative design ». International Journal of Architectural Computing 17, no 1 (mars 2019) : 88–102. http://dx.doi.org/10.1177/1478077119832465.
Texte intégralRésumé :
This article will focus on abstracting and generalising a well-studied paradigm in visual, event-related potential based brain–computer interfaces, for the spelling of characters forming words, into the visually encoded discrimination of shape features forming design aggregates. After identifying typical technologies in neuroscience and neuropsychology of high interest for integrating fast cognitive responses into generative design and proposing the machine learning model of an ensemble of linear classifiers in order to tackle the challenging features that electroencephalography data carry, it will present experiments in encoding shape features for generative models by a mechanism of visual context updating and the computational implementation of vision as inverse graphics, to suggest that discriminative neural phenomena of event-related potentials such as P300 may be used in a visual articulation strategy for modelling in generative design.
47
He, Junpeng, Lei Luo, Kun Xiao, Xiyu Fang et Yun Li. « Generate qualified adversarial attacks and foster enhanced models based on generative adversarial networks ». Intelligent Data Analysis 26, no 5 (5 septembre 2022) : 1359–77. http://dx.doi.org/10.3233/ida-216134.
Texte intégralRésumé :
In cybersecurity, intrusion detection systems (IDSes) are of vital importance, allowing different companies and their departments to identify malicious attacks from magnanimous network traffic; however, the effectiveness and stability of these artificial intelligence-based systems are challenged when coping with adversarial attacks. This work explores a creative framework based on a generative adversarial network (GAN) with a series of training algorithms that aims to generate instances of adversarial attacks and utilize them to help establish a new IDS based on a neural network that can replace the old IDS without knowledge of any of its parameters. Furthermore, to verify the quality of the generated attacks, a transfer mechanism is proposed for calculating the Frechet inception distance (FID). Experiments show that based on the original CICIDS2017 dataset, the proposed framework can generate four types of adversarial attacks (DDoS, DoS, Bruteforce, and Infiltration), which precipitate four types of classifiers (Decision Tree, Random Forest, Adaboost, and Deep Neural Network), set as black-box old IDSes, with low detection rates; additionally, the IDSes that the proposed framework newly establish have an average detection rate of 98% in coping with both generated adversarial and original attacks.
48
Wang, Chenyue, Linlin Zhang, Kai Zhao, Xuhui Ding et Xusheng Wang. « AdvAndMal : Adversarial Training for Android Malware Detection and Family Classification ». Symmetry 13, no 6 (17 juin 2021) : 1081. http://dx.doi.org/10.3390/sym13061081.
Texte intégralRésumé :
In recent years, Android malware has continued to evolve against detection technologies, becoming more concealed and harmful, making it difficult for existing models to resist adversarial sample attacks. At the current stage, the detection result is no longer the only criterion for evaluating the pros and cons of the model with its algorithms, it is also vital to take the model’s defensive ability against adversarial samples into consideration. In this study, we propose a general framework named AdvAndMal, which consists of a two-layer network for adversarial training to generate adversarial samples and improve the effectiveness of the classifiers in Android malware detection and family classification. The adversarial sample generation layer is composed of a conditional generative adversarial network called pix2pix, which can generate malware variants to extend the classifiers’ training set, and the malware classification layer is trained by RGB image visualized from the sequence of system calls. To evaluate the adversarial training effect of the framework, we propose the robustness coefficient, a symmetric interval i = [−1, 1], and conduct controlled experiments on the dataset to measure the robustness of the overall framework for the adversarial training. Experimental results on 12 families with the largest number of samples in the Drebin dataset show that the accuracy of the overall framework is increased from 0.976 to 0.989, and its robustness coefficient is increased from 0.857 to 0.917, which proves the effectiveness of the adversarial training method.
49
Heesch, Mateusz, Michał Dziendzikowski, Krzysztof Mendrok et Ziemowit Dworakowski. « Diagnostic-Quality Guided Wave Signals Synthesized Using Generative Adversarial Neural Networks ». Sensors 22, no 10 (19 mai 2022) : 3848. http://dx.doi.org/10.3390/s22103848.
Texte intégralRésumé :
Guided waves are a potent tool in structural health monitoring, with promising machine learning algorithm applications due to the complexity of their signals. However, these algorithms usually require copious amounts of data to be trained. Collecting the correct amount and distribution of data is costly and time-consuming, and sometimes even borderline impossible due to the necessity of introducing damage to vital machinery to collect signals for various damaged scenarios. This data scarcity problem is not unique to guided waves or structural health monitoring, and has been partly addressed in the field of computer vision using generative adversarial neural networks. These networks generate synthetic data samples based on the distribution of the data they were trained on. Though there are multiple researched methods for simulating guided wave signals, the problem is not yet solved. This work presents a generative adversarial network architecture for guided waves generation and showcases its capabilities when working with a series of pitch-catch experiments from the OpenGuidedWaves database. The network correctly generates random signals and can accurately reconstruct signals it has not seen during training. The potential of synthetic data to be used for training other algorithms was confirmed in a simple damage detection scenario, with the classifiers trained exclusively on synthetic data and evaluated on real signals. As a side effect of the signal reconstruction process, the network can also compress the signals by 98.44% while retaining the damage index information they carry.
50
Li, Jie, Boyu Zhao, Kai Wu, Zhicheng Dong, Xuerui Zhang et Zhihao Zheng. « A Representation Generation Approach of Transmission Gear Based on Conditional Generative Adversarial Network ». Actuators 10, no 5 (23 avril 2021) : 86. http://dx.doi.org/10.3390/act10050086.
Texte intégralRésumé :
Gear reliability assessment of vehicle transmission has been a challenging issue of determining vehicle safety in the transmission industry due to a significant amount of classification errors with high-coupling gear parameters and insufficient high-density data. In terms of the preprocessing of gear reliability assessment, this paper presents a representation generation approach based on generative adversarial networks (GAN) to advance the performance of reliability evaluation as a classification problem. First, with no need for complex modeling and massive calculations, a conditional generative adversarial net (CGAN) based model is established to generate gear representations through discovering inherent mapping between features with gear parameters and gear reliability. Instead of producing intact samples like other GAN techniques, the CGAN based model is designed to learn features of gear data. In this model, to raise the diversity of produced features, a mini-batch strategy of randomly sampling from the combination of raw and generated representations is used in the discriminator, instead of using all of the data features. Second, in order to overcome the unlabeled ability of CGAN, a Wasserstein labeling (WL) scheme is proposed to tag the created representations from our model for classification. Lastly, original and produced representations are fused to train classifiers. Experiments on real-world gear data from the industry indicate that the proposed approach outperforms other techniques on operational metrics.