scholarly journals Dynamics of Fourier Modes in Torus Generative Adversarial Networks

Mathematics ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 325
Author(s):  
Ángel González-Prieto ◽  
Alberto Mozo ◽  
Edgar Talavera ◽  
Sandra Gómez-Canaval
Keyword(s):  
Fourier Series ◽  
Generative Adversarial Networks ◽  
Learning Models ◽  
Training Process ◽  
Small Perturbations ◽  
Adversarial Networks ◽  
Novel Method ◽  
Truncated Fourier Series ◽  
Real Flow ◽  
Machine Learning Models

Generative Adversarial Networks (GANs) are powerful machine learning models capable of generating fully synthetic samples of a desired phenomenon with a high resolution. Despite their success, the training process of a GAN is highly unstable, and typically, it is necessary to implement several accessory heuristics to the networks to reach acceptable convergence of the model. In this paper, we introduce a novel method to analyze the convergence and stability in the training of generative adversarial networks. For this purpose, we propose to decompose the objective function of the adversary min–max game defining a periodic GAN into its Fourier series. By studying the dynamics of the truncated Fourier series for the continuous alternating gradient descend algorithm, we are able to approximate the real flow and to identify the main features of the convergence of GAN. This approach is confirmed empirically by studying the training flow in a 2-parametric GAN, aiming to generate an unknown exponential distribution. As a by-product, we show that convergent orbits in GANs are small perturbations of periodic orbits so the Nash equillibria are spiral attractors. This theoretically justifies the slow and unstable training observed in GANs.

scholarly journals Counterfactual Examples for Data Augmentation: A Case Study

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Md Golam Moula Mehedi Hasan ◽  
Douglas A. Talbert
Keyword(s):  
Machine Learning ◽  
Potential Application ◽  
Data Augmentation ◽  
Generative Adversarial Networks ◽  
Application Area ◽  
Learning Models ◽  
Adversarial Networks ◽  
Feature Values ◽  
Machine Learning Models

Counterfactual explanations are gaining in popularity as a way of explaining machine learning models. Counterfactual examples are generally created to help interpret the decision of a model. In this case, if a model makes a certain decision for an instance, the counterfactual examples of that instance reverse the decision of the model. The counterfactual examples can be created by craftily changing particular feature values of the instance. Though counterfactual examples are generated to explain the decision of machine learning models, in this work, we explore another potential application area of counterfactual examples, whether counterfactual examples are useful for data augmentation. We demonstrate the efficacy of this approach on the widely used “Adult-Income” dataset. We consider several scenarios where we do not have enough data and use counterfactual examples to augment the dataset. We compare our approach with Generative Adversarial Networks approach for dataset augmentation. The experimental results show that our proposed approach can be an effective way to augment a dataset.

scholarly journals Prospects for Generative - Adversarial Networks in Network Traffic Classification Tasks

2021 ◽  
Vol 2096 (1) ◽  
pp. 012174
Author(s):  
G D Asyaev
Keyword(s):  
Machine Learning ◽  
Network Traffic ◽  
Training Sample ◽  
Generative Adversarial Networks ◽  
Traffic Classification ◽  
Learning Models ◽  
Generative Adversarial Network ◽  
Adversarial Networks ◽  
Network Traffic Classification ◽  
Machine Learning Models

Abstract The paper presents an approach that allows increasing the training sample and reducing class imbalance for traffic classification problems. The basic principles and architecture of generative adversarial networks are considered. The mathematical model of network traffic classification is described. The training sample taken to solve the problem has been analyzed. The data proprocessing is carried out and justified. An architecture of the generative-adversarial network is constructed and an algorithm for generating new features is developed. Machine learning models for traffic classification problem were considered and built: Logistic regression, k Nearest Neighbors, Decision tree, Random forest. A comparative analysis of the results of machine learning models without and with the generation of new features is conducted. The obtained results can be applied both in the tasks of network traffic classification, and in general cases of multiclass classification and exclusion of unbalanced features.

scholarly journals Inverse Airfoil Design Method for Generating Varieties of Smooth Airfoils Using Conditional WGAN-GP

2021 ◽  
Author(s):  
Kazuo Yonekura ◽  
Nozomu Miyamoto ◽  
Katsuyuki Suzuki
Keyword(s):  
Machine Learning ◽  
Design Method ◽  
Lift Coefficient ◽  
Flow Analysis ◽  
Generative Adversarial Networks ◽  
Learning Models ◽  
Smoothing Methods ◽  
Adversarial Networks ◽  
Proposed Model ◽  
Machine Learning Models

Abstract Machine learning models are recently utilized for airfoil shape generation methods. It is desired to obtain airfoil shapes that satisfies required lift coefficient. Generative adversarial networks (GAN) output reasonable airfoil shapes. However, shapes obtained from ordinal GAN models are not smooth, and they need smoothing before flow analysis. Therefore, the models need to be coupled with B'ezier curves or other smoothing methods to obtain smooth shapes. Generating shapes without any smoothing methods is challenging. In this study, we employed conditional Wasserstein GAN with gradient penalty (CWGAN-GP) to generate airfoil shapes, and the obtained shapes are as smooth as those obtained using smoothing methods. With the proposed method, no additional smoothing method is needed to generate airfoils. Moreover, the proposed model outputs shapes that satisfy the lift coefficient requirements.

scholarly journals A New Integrated Approach for Landslide Data Balancing and Spatial Prediction Based on Generative Adversarial Networks (GAN)

2021 ◽  
Vol 13 (19) ◽  
pp. 4011
Author(s):  
Husam A. H. Al-Najjar ◽  
Biswajeet Pradhan ◽  
Raju Sarkar ◽  
Ghassan Beydoun ◽  
Abdullah Alamri
Keyword(s):  
Machine Learning ◽  
Spatial Prediction ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Slope Aspect ◽  
Support Vector ◽  
Learning Models ◽  
Adversarial Networks ◽  
Landslide Data ◽  
Machine Learning Models

Landslide susceptibility mapping has significantly progressed with improvements in machine learning techniques. However, the inventory / data imbalance (DI) problem remains one of the challenges in this domain. This problem exists as a good quality landslide inventory map, including a complete record of historical data, is difficult or expensive to collect. As such, this can considerably affect one’s ability to obtain a sufficient inventory or representative samples. This research developed a new approach based on generative adversarial networks (GAN) to correct imbalanced landslide datasets. The proposed method was tested at Chukha Dzongkhag, Bhutan, one of the most frequent landslide prone areas in the Himalayan region. The proposed approach was then compared with the standard methods such as the synthetic minority oversampling technique (SMOTE), dense imbalanced sampling, and sparse sampling (i.e., producing non-landslide samples as many as landslide samples). The comparisons were based on five machine learning models, including artificial neural networks (ANN), random forests (RF), decision trees (DT), k-nearest neighbours (kNN), and the support vector machine (SVM). The model evaluation was carried out based on overall accuracy (OA), Kappa Index, F1-score, and area under receiver operating characteristic curves (AUROC). The spatial database was established with a total of 269 landslides and 10 conditioning factors, including altitude, slope, aspect, total curvature, slope length, lithology, distance from the road, distance from the stream, topographic wetness index (TWI), and sediment transport index (STI). The findings of this study have shown that both GAN and SMOTE data balancing approaches have helped to improve the accuracy of machine learning models. According to AUROC, the GAN method was able to boost the models by reaching the maximum accuracy of ANN (0.918), RF (0.933), DT (0.927), kNN (0.878), and SVM (0.907) when default parameters used. With the optimum parameters, all models performed best with GAN at their highest accuracy of ANN (0.927), RF (0.943), DT (0.923) and kNN (0.889), except SVM obtained the highest accuracy of (0.906) with SMOTE. Our finding suggests that RF balanced with GAN can provide the most reasonable criterion for landslide prediction. This research indicates that landslide data balancing may substantially affect the predictive capabilities of machine learning models. Therefore, the issue of DI in the spatial prediction of landslides should not be ignored. Future studies could explore other generative models for landslide data balancing. By using state-of-the-art GAN, the proposed model can be considered in the areas where the data are limited or imbalanced.

Towards High-Performance Deep Learning Models in Tool Wear Classification with Generative Adversarial Networks

2021 ◽  
pp. 117484
Author(s):  
Dirk Alexander Molitor ◽  
Christian Kubik ◽  
Marco Becker ◽  
Ruben Helmut Hetfleisch ◽  
Fan Lyu ◽  
...  
Keyword(s):  
Deep Learning ◽  
Tool Wear ◽  
High Performance ◽  
Generative Adversarial Networks ◽  
Learning Models ◽  
Adversarial Networks ◽  
Tool Wear Classification

scholarly journals Modelling and forecasting art movements with CGANs

2020 ◽  
Vol 7 (4) ◽  
pp. 191569
Author(s):  
Edoardo Lisi ◽  
Mohammad Malekzadeh ◽  
Hamed Haddadi ◽  
F. Din-Houn Lau ◽  
Seth Flaxman
Keyword(s):  
Generative Adversarial Networks ◽  
Vector Autoregressive ◽  
Adversarial Networks ◽  
Latent Distribution ◽  
Small Set ◽  
One Step ◽  
Temporal Aspect ◽  
Novel Method ◽  
The Mean ◽  
Modelling And Forecasting

Conditional generative adversarial networks (CGANs) are a recent and popular method for generating samples from a probability distribution conditioned on latent information. The latent information often comes in the form of a discrete label from a small set. We propose a novel method for training CGANs which allows us to condition on a sequence of continuous latent distributions f (1) , …, f ( K ) . This training allows CGANs to generate samples from a sequence of distributions. We apply our method to paintings from a sequence of artistic movements, where each movement is considered to be its own distribution. Exploiting the temporal aspect of the data, a vector autoregressive (VAR) model is fitted to the means of the latent distributions that we learn, and used for one-step-ahead forecasting, to predict the latent distribution of a future art movement f ( K +1) . Realizations from this distribution can be used by the CGAN to generate ‘future’ paintings. In experiments, this novel methodology generates accurate predictions of the evolution of art. The training set consists of a large dataset of past paintings. While there is no agreement on exactly what current art period we find ourselves in, we test on plausible candidate sets of present art, and show that the mean distance to our predictions is small.

A novel method to improve vertical accuracy of CARTOSAT DEM using machine learning models

2020 ◽  
Vol 13 (4) ◽  
pp. 1139-1150 ◽  
Author(s):  
Venkatesh Kasi ◽  
Pavan Kumar Yeditha ◽  
Maheswaran Rathinasamy ◽  
Ramdas Pinninti ◽  
Sankar Rao Landa ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Models ◽  
Novel Method ◽  
Vertical Accuracy ◽  
Cartosat Dem ◽  
Machine Learning Models

An anomaly detection method based on double encoder–decoder generative adversarial networks

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Hui Liu ◽  
Tinglong Tang ◽  
Jake Luo ◽  
Meng Zhao ◽  
Baole Zheng ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Latent Variables ◽  
Dimensional Space ◽  
Superior Performance ◽  
Generative Adversarial Networks ◽  
Training Process ◽  
Content Type ◽  
Detection Model ◽  
Adversarial Networks ◽  
Low Dimensional

Purpose This study aims to address the challenge of training a detection model for the robot to detect the abnormal samples in the industrial environment, while abnormal patterns are very rare under this condition. Design/methodology/approach The authors propose a new model with double encoder–decoder (DED) generative adversarial networks to detect anomalies when the model is trained without any abnormal patterns. The DED approach is used to map high-dimensional input images to a low-dimensional space, through which the latent variables are obtained. Minimizing the change in the latent variables during the training process helps the model learn the data distribution. Anomaly detection is achieved by calculating the distance between two low-dimensional vectors obtained from two encoders. Findings The proposed method has better accuracy and F1 score when compared with traditional anomaly detection models. Originality/value A new architecture with a DED pipeline is designed to capture the distribution of images in the training process so that anomalous samples are accurately identified. A new weight function is introduced to control the proportion of losses in the encoding reconstruction and adversarial phases to achieve better results. An anomaly detection model is proposed to achieve superior performance against prior state-of-the-art approaches.

Sign in / Sign up

Export Citation Format

Share Document