Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 238 for “"Generative Adversarial Networks (GANs)"”.
-
Image Data Augmentation from Small Training Datasets Using Generative Adversarial Networks (GANs)
… enhances the effectiveness of data augmentation. Generative adversarial networks (GANs), one of the learning-based generative models, have made remarkable advances in data synthesis. However, GANs still face many challenges in generating high-quality augmented images from small datasets because …
-
Facial Expression Recognition Using Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) for Data Augmentation and Image Generation
… area of research, with Convolutional Neural Networks (CNNs) being widely employed for classification. In this research, we propose a CNN-based approach for FER that utilizes both original and augmented datasets to enhance classification accuracy. Experimental results on the FER2013 dataset …
-
An Introduction to Generative Adversarial Networks
… thesis is a survey of the mathematical theory of Generative Adversarial Networks (GANs). The relevant theories discussed are game theory, information theory and optimal transport theory.
-
A Study on Distribution Learning of Generative Adversarial Networks
… is an exploration of the properties of shallow generative adversarial networks (GANs). We focus on several aspects of GANs to investigate the learnability of a class of distributions using shallow GANs and conduct experiments to explore the influence of these aspects on the performance of the …
-
Generative Adversarial Networks Based on a General Parameterized Family of Generator Loss Functions
… parameterized generator loss function for generative adversarial networks (GANs). We establish an equilibrium theorem for our resulting GAN system under a canonical discriminator in terms of the so-called Jensen-$f$-divergence, a natural generalization of the Jensen-Shannon divergence to …
-
Comparison of methods for creating populations of models by solving stochastic inverse problems
… inverse problems. In recent years, however, Generative Adversarial Networks (GANs) have been employed. The effectiveness of Markov Chain Monte Carlo methods as compared to a conditional generative adversarial network (cGAN) when applied to a family of models produced by a system of ordinary …
-
A Theory of Generative Models and Robustness via Regularization
… optimal policies. On the other hand, Generative Adversarial Networks (GANs) employ regularization for computational purposes, avoiding instability in training. Despite the widespread use and multi-faceted motivation of regularization, extensive evidence has suggested that …
-
Differential Privacy and Econometric Methods
… to this synthetic data. I will do this using generative adversarial networks (GANs). In doing so, I will also explore other differentially private methods for econometric estimators, as well as explore ways to achieve consistent standard errors when reporting these estimators.
-
Bayesian Variable Selection with Shrinkage Priors and Generative Adversarial Networks for Fraud Detection
… fraud detection in the financial industry using Generative Adversarial Networks (GANs) in conjunction with Uni and Multi Variate Bayesian Model with Shrinkage Priors (BMSP). The problem addressed is the need for accurate and advanced fraud detection techniques due to the increasing sophistication …
-
Machine Learning for 3D Visualisation Using Generative Models
… in the past ten years is the introduction of generative adversarial networks (GANs), which had achieved great success in their ability to generate images comparable to real photos with minimum human intervention. These networks can generalise to a multitude of desired outputs, especially in …
-
Machine Learning for 3D Visualisation Using Generative Models
… in the past ten years is the introduction of generative adversarial networks (GANs), which had achieved great success in their ability to generate images comparable to real photos with minimum human intervention. These networks can generalise to a multitude of desired outputs, especially in …
-
Generative methods for image synthesis with applications to medical imaging
… for diagnostic and analytical improvements. Generative methods for image synthesis have been an active area of research in recent years. In this thesis, we explore the use of a hybrid model of generative adversarial networks (GANs) and transformer networks for image synthesis. We propose a …
-
Time Series Forecasting Using Generative Adversarial Networks
… and improving resource allocation. Recently, Generative Adversarial Networks (GANs) have been used to learn from these features to aid in time-series forecasting. We propose a novel framework that utilizes the unsupervised paradigm of a GAN based on related research called TimeGAN. Instead of …
-
Postprocessing GAN-Generated Synthetic Time Series Using Dynamic Time Warping
Generative Adversarial Networks (GANs) are a class of deep learning models capable of producing realistic synthetic data that preserve the statistical and temporal characteristics of real datasets. The DoppelGANger (DGAN) framework extends this approach to time series data by jointly modeling …
-
Automatinis žaidimų lygių generavimas naudojant dirbtinį intelektą /
… methods are implemented and compared: ● Generative Adversarial Networks (GANs), trained on manually generated level datasets; ● Markov chains using tile transition probabilities; ● Wave Function Collapse (WFC), a constraint-based algorithm inspired by pixel pattern synthesis. The …
-
AI-Assisted Pipeline for 3D Face Avatar Generation
… and human labour. This thesis leverages generative models like Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAEs) to automate avatar creation. Our pipeline offers control over three aspects: face shape, skin color, and fine details like beards or wrinkles. This …
-
Machine Learning-Aided Aerospace Applications with Generative Adversarial Networks
Applied generative machine-learning models have demonstrated exceptional accuracy at recreating realistic data, becoming a highly researched field in aerospace and defense technologies. Generative Adversarial Networks (GANs), a subset of generative models, have shown remarkable proficiency at this …
-
Understanding and Improving Generative Adversarial Networks in Low-Data Settings
Generative Adversarial Networks (GANs) have emerged as a powerful tool in machine learning, excelling at generating realistic data through adversarial training between a generator and a discriminator. Despite their success, training GANs remains challenging, particularly in low-data settings, where …
-
EXTENDED SEMI-SUPERVISED LEARNING GENERATIVE ADVERSARIAL NETWORKS FOR FEATURE ANALYSIS AND CLASSIFICATION OF HYPERSPECTRAL IMAGERY
… to analyze. One deep learning approach, generative adversarial networks (GANs), has been shown to be very effective in classification and generation of accurate synthetic data in computer vision problems. In this work we propose extended semi-supervised learning (ESSL) GAN and show that …
-
Recovery of high-resolution magnetic field distribution inside the brain from limited MRI data using machine learning prior
… of scan time. Recent advances in deep neural networks, particularly the generative adversarial networks (GANs), can learn the prior information through examples and generate the high-resolution field map using only one low-resolution field map counter- part. In this work, we apply the deep …
Page 1 of 12