Sökning: "WGAN-GP"

Hittade 4 uppsatser innehållade ordet WGAN-GP.

1. 1. Scenario Generation for Stress Testing Using Generative Adversarial Networks : Deep Learning Approach to Generate Extreme but Plausible Scenarios

   Uppsats för yrkesexamina på avancerad nivå, Umeå universitet/Institutionen för matematik och matematisk statistik

   Författare :Jonas Gustafsson; Conrad Jonsson; [2023]
   Nyckelord :Machine Learning; Generative Adversarial Network GAN ; Wasserstein Generative Adversarial Network WGAN ; Scenario Generation; Stress Testing; Central Counterparty Clearing;

   Sammanfattning : Central Clearing Counterparties play a crucial role in financial markets, requiring robust risk management practices to ensure operational stability. A growing emphasis on risk analysis and stress testing from regulators has led to the need for sophisticated tools that can model extreme but plausible market scenarios. LÄS MER

3. 2. Generative Adversarial Networks in Lip-Synchronized Deepfakes for Personalized Video Messages

   Master-uppsats, Lunds universitet/Matematik LTH

   Författare :Johan Liljegren; Pontus Nordqvist; [2021]
   Nyckelord :Generative Adversarial Networks; GAN; Lip-Synchronization; Deepfake; Deep Learning; Autoencoder; WGAN; WGAN-GP; L1WGAN-GP; Skip-Connections; FID-Score; Mathematics and Statistics; Technology and Engineering;

   Sammanfattning : The recent progress of deep learning has enabled more powerful frameworks to create good-quality deepfakes. Deepfakes, which are mostly known for malicious purposes, have great potential to be useful in areas such as the movie industry, education, and personalized messaging. LÄS MER

4. 3. Value at Risk Estimation with Generative Adversarial Networks

   Magister-uppsats, Lunds universitet/Statistiska institutionen

   Författare :David Tobjörk; [2021]
   Nyckelord :generative adversarial networks value at risk finance machine learning neural networks; Mathematics and Statistics;

   Sammanfattning : Risk is of large importance for financial institutions and there are many different measures that can be used. A popular one is value at risk (VaR), which is the maximum likely loss for a portfolio of financial assets. Different methods of estimating it has been suggested, one often described is the variance-covariance method. LÄS MER

5. 4. Investigating the Learning Behavior of Generative Adversarial Networks

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Simon Westberg; [2021]
   Nyckelord :;

   Sammanfattning : Since their introduction in 2014, generative adversarial networks (GANs) have quickly become one of the most popular and successful frameworks for training deep generative models. GANs have shown exceptional results on different image generation tasks and they are known for their ability to produce realistic high- resolution images. LÄS MER