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 39 for “"Mode collapse"”.
-
PacGAN: The power of two samples in generative adversarial networks
… innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable recent improvements in generating realistic images, one of their major shortcomings is the fact that in practice, they tend to produce samples with little diversity, even when …
-
Improving Implicit Generative Models via Online Kernel Methods
… training behaviors of \gls{gans}, including mode collapse and cycling, by using online kernel-based non-parametric classifiers. One of the major breakthroughs in machine learning over the past several years has been \gls{gans}, a neural network-based implicit generative model which aims to …
-
Memorization in Generative Networks and Mixtures of GANs
… fitting the training data) is necessary to avoid mode collapse in generative networks. Using a straightforward measure of the distance between the training data points and the closest point in the range of the generator, we study how well current generative models memorize in terms of the training …
-
Generative Adversarial Networks and Word Embeddings for Natural Language Generation
… then be used to train a generative adversarial model. The output of the model’s generator are word matrices which can then be translated back into sentences using closest cosine similarity. Four models were designed and trained including two Deep Convolutional Generative Adversarial Networks …
-
Variational inference and normalising flows for gravitational wave parameter estimation
… with the main obstacle identified to be mode collapse fuelled by the reverse Kullback-Leibler divergence training objective. Different strategies of mitigating the mode collapse problem are investigated, with best improvements seen from posterior temperature annealing. The thesis further …
-
Gilieji generatyviniai modeliai Baltijos akcijų grąžoms: Empirinis Wasserstein GAN vertinimas /
… non-linear dependencies. Traditional econometric models (ARMA, GARCH) can capture linear dependencies and conditional volatility, but often inadequately describe more complex relationships and quick market changes. Generative Adversarial Networks (GAN) offer a flexible approach to modeling complex …
-
Iterative Clustering for Memory-Assisted Reinforcement Learning in De Novo Drug Design Language Models
… for de novo molecular design often suffers from mode collapse, where the policy rapidly concentrates on narrow regions of chemical space at the expense of structural diversity. This thesis presents a modular approach for combining experience replay and clustering approaches to enhance diversity …
-
Deep Learning Framework for Graph-Based Molecular Drug Discovery
… metrics, and the right dropout ratio avoids mode collapse. Additionally, Conditional GraphGANFed (cGraphGANFed) incorporates a critic network from Reinforcement Learning (RL) to meet specific client requirements. cGraphGANFed can optimize for particular metrics, producing molecules with …
-
Multi-scale, Multi-dimensional Reservoir Characterization Using Advanced Analytics and Machine Learning
… and quantification of uncertainty in reservoir models. In the next section a novel Generative Adversarial Network (GAN) architecture is introduced which can generate realistic geological models while maintaining the variability of the generated dataset. The concept of mode collapse and its …
-
Magnetinio rezonanso tomografijos vaizdų segmentavimas taikant mokymąsi iš keleto pavyzdžių /
… several issues: an overly strong discriminator, mode collapse, and the generator's difficulty in creating images with deeper relationships. This work proposes integrating a relation module into the discriminator of feature-matching generative adversarial networks to address these challenges. The …
-
Mitigating the challenges of distribution shift under strong computational constraints
… learning in enabling efficient and adaptable models suitable for resource-constrained environments. The Diversified Dynamic Routing (DivDR) method showcases the potential of unsupervised clustering for efficient image recognition, while the Domain Partitioning Network (DoPaNet) tackles mode …
-
Generative Artificial Intelligence for Secure and Efficient Intrusion Detection in Imbalanced Multi-Attack Cyber Environments
The rapid expansion of modern cyber infrastructures, including cloud computing, Internet of Things (IoT) ecosystems, industrial control systems, cyber-physical environments, and large-scale enterprise networks, has significantly increased the complexity and sophistication of cyber threats. …
-
Generative modelling under epistemic uncertainty
… that ensures scalability, this framework allows models to explicitly represent ignorance. While we validate these principles through Random-Set Neural Networks (RS-NN) for classification and a Unified Evaluation Framework, the primary contribution of this work lies in re-imagining Generative AI …
-
Steps Towards the Pluralistic Alignment of Language Models
… preferences. Specifically, I use large language models (LLMs) as a test-bed for pluralistic alignment.I first motivate the need for pluralism in alignment, outlining failure modes and risks of either assuming that value variation either doesn't exist or ignoring such variation. I propose a …
-
Generating Realistic Labeled Graphs with Conditional Generative Models
… We first introduce a conditional WGAN-GP model that integrates class information into both the generator and a Graph Neural Network (GNN) critic. This framework improves training stability and mode collapse. We further extend this framework by introducing a density-aware generation …
-
Enhancing Histopathology Image Generation with Diffusion Generative Models: A Comprehensive Study
… and training of effective deep learning models. Generative Adversarial Networks (GANs) have previously attempted to address these issues by creating synthetic data but suffer mode collapse, which reduces their effectiveness and reliability. This study explores Diffusion Generative Models …
-
Long video generation using the VAE-GAN method
… addresses these challenges through novel hybrid models and transformer-based architectures, improving video quality, efficiency, and duration. The thesis first analyses limitations of existing generative models. While GANs produce sharp videos but suffer from computational expense and mode …
-
Towards Explainable Generative Adversarial Networks
… why object classes can be omitted resulting in mode-dropping or mode collapse. We also create a new "Discriminative Score" for each object, and we show that their distribution is correlated with this score. Finally, we performed an experiment to determine whether missing details are a result of …
-
Optimal Transport, Congested Transport, and Wasserstein Generative Adversarial Networks
… one can ameliorate a transient form of mode collapse in the optimal mass flows. The second part of this thesis presents new algorithms for generative modelling based on insights from optimal transport theory. The basic idea is to transform one distribution into another via iterated …
-
Innovative Solutions for Data Accessibility: Utilizing Synthetic Data in DEWA Operations
Smart‑meter data are pivotal to modern demand‑side management and predictive maintenance, yet strict confidentiality rules at Dubai Electricity and Water Authority (DEWA) hinder internal access. Synthetic data generated by Generative Adversarial Networks (GANs) offers a promising privacy‑preserving …
Page 1 of 2