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 17 of 17 for “"WGAN-GP"”.
-
Optimal Transport, Congested Transport, and Wasserstein Generative Adversarial Networks
… data. Wasserstein GANs with Gradient Penalty (WGAN-GP) [GAA+17] were designed to update $\mu$ by computing and then minimizing the Wasserstein 1 distance between $\mu$ and $\nu$. In the first part of this thesis we show that in fact, WGAN-GP do not compute this distance. Instead, they compute …
-
A MULTI-LOSS WASSERSTEIN GAN FRAMEWORK FOR GEOSTATISTICAL SIMULATION
… Adversarial Network with Gradient Penalty (WGAN-GP) framework as an innovative tool for geostatistical simulation. The proposed framework leverages the WGAN-GP architecture alongside multi-loss functions, including feature matching loss, pixel intensity loss, structural similarity index …
-
Causal discovery from observational tabular data with generative adversarial learning
… Adversarial Network with Gradient Penalty (WGAN-GP) framework toaddress key limitations: (1) model overfitting from simplistic loss functions; (2) dependence on single parametric assumptions that hinder accurate causal graph recoveryreflective of true data relationships; (3) high …
-
Integrating Seismic Attributes And Machine Learning For Accurate 3D Petrophysical And Geomechanical Modeling In Shale Plays
… Adversarial Networks with Gradient Penalty (WGAN-GP), to enhance predictive accuracy.LSTMs and TCNs effectively capture temporal dependencies, while WGAN-GP generates high-quality synthetic data to mitigate data scarcity. The study critically evaluates existing 3D modeling methodologies, …
-
Generative Adversarial Networks and Word Embeddings for Natural Language Generation
… by using Wasserstein GANs with gradient penalty (WGAN-GP) we were able to successfully train models with no mode collapse, whose generator outputs were reasonably well-formed. Model generators’ outputs were evaluated by well-formedness using a pretrained BERT language model, and by uniqueness …
-
Generování obličejů s pomocí podmíněných generativních neuronových sítí
… porovnány výsledky z modelů architektur DCGAN, WGAN-GP a ProGAN, k jejichž implementaci bylo využito knihovny Tensorflow. Trénování modelů neuronových sítí probíhalo na datové sadě Flickr-Faces-HQ. Napříč všemi použitými architekturami se podařilo natrénovat modely generující realistické lidské …
-
Generating Realistic Labeled Graphs with Conditional Generative Models
… Adversarial Networks with Gradient Penalty (WGAN-GP). 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 …
-
Generativní oponentní neuronové sítě zachovávající identitu otisku prstu
… viacero trénovacích algoritmov, z ktorých WGAN-GP dosahuje najlepšie výsledky. Jednotlivé modely sú porovnávané kombináciou metrík FID a Rank-1 accuracy pri porovnávaní generovaných obrázkov s originálnymi vstupnými binarizovanými odtlačkami. Najlepšie modely sú vybrané ako Pareto optimálne …
-
Simulace projevu kožního onemocnění s využitím GAN
… ekzém. Sieť generátoru z natrénovaného WGAN-GP modelu bola použitá na vygenerovanie datasetov syntetických odtlačkov prstov. Tieto syntetické odtlačky boli porovnané s reálnymi odtlačkami s využitím NFIQ a FiQiVi nástrojov na určenie kvality spoločne s porovnaním rozložení lokácií a …
-
Computational finance and forecasting methods
… the Wasserstein Generative Adversarial Network (WGAN-GP) for a detailed analysis of Bitcoin's price behavior under various market conditions. The Lévy-Khintchine process captures extreme price changes, while WGAN-GP tests the robustness of these predictions, showing high accuracy in extreme …
-
Generativní neuronová síť pro tvorbu syntetických hudebních frází
… z Wassersteinova GANu s penalizací gradientu (WGAN-GP), který je doplněn o spektrální normalizaci v diskriminátoru a mechanismus vícehlavé pozornosti v generátoru. Pro trénink byla zvolena žánrově pestrá databáze Lakh MIDI Dataset, z níž byly extrahovány monofonní melodické party a …
-
Multi-scale, Multi-dimensional Reservoir Characterization Using Advanced Analytics and Machine Learning
… and Wasserstein GAN with gradient penalty (WGAN-GP). The results show that the proposed architecture significantly enhances variability and reduces the spatial bias induced by mode collapse, outperforming both DCGAN and WGAN-GP in the application of generating subsurface property …
-
TransFURmer: Hair and Fur rendering using SwinIR - Transformer-based Neural Rendering of Hair and Fur using SwinIR
… loss, and Wasserstein GAN with gradient penalty (WGAN-GP) loss, to accurately reconstruct the fine details and improve perceptual realism. The final model successfully generalizes to unseen geometry and the implemented FFT and LPIPS loss proved highly effective at preserving the texture of …
-
Crossdocking vs. Traditional Warehousing: Small-Sample Data Augmentation to Assess Product Suitability
… data for generative adversarial networks. The WGAN-GP used in the thesis is constructed from a three-layer generator and discriminator with dropout later and activation function of tan h (hyperbolic tangent). Following that, we construct a multi-layer perceptron architecture network for the …
-
Subsurface characterization using deep learning theory and techniques
… Adversarial Network with Gradient Penalty (WGAN-GP) and the Denoising Diffusion Implicit Model (DDIM). The generators of the trained generative models are used to generate complex permeability fields from latent space, and ES-MDA is then used to update the latent variables by assimilating …
-
Efficient Gan-Based Adversarial Example Generation Against Ml-Based Network Intrusion Detection Systems
In the realm of network security, Network Intrusion Detection Systems (NIDS) are essential for identifying and mitigating malicious activities targeting networked devices. Traditionally, these systems have relied on signature-based and anomaly-based detection techniques. However, the increasing …
-
Generativní neuronová síť pro tvorbu syntetických hudebních frází
Tato práce se zabývá generováním syntetických hudebních frází pomocí generativních neuronových sítí (GAN) a především otázkou, jak lze kvalitu takto vytvořeného materiálu měřit. Cílem bylo navrhnout a implementovat model pro symbolickou reprezentaci hudby a doplnit jej opakovatelným postupem …