Essays about: "WGAN"

Showing result 1 - 5 of 8 essays containing the word WGAN.

  1. 1. Fast Simulations of Radio Neutrino Detectors : Using Generative Adversarial Networks and Artificial Neural Networks

    University essay from Uppsala universitet/Högenergifysik

    Author : Anton Holmberg; [2022]
    Keywords : Askaryan emission; Radio detection of neutrinos; in-ice propagation; neutrino; Generative adversarial networks; GAN; WGAN; Neural networks; NN; surrogate model; IceCube; deep learning; generative model;

    Abstract : Neutrino astronomy is expanding into the ultra-high energy (>1017eV) frontier with the use of in-ice detection of Askaryan radio emission from neutrino-induced particle showers. There are already pilot arrays for validating the technology and the next few years will see the planning and construction of IceCube-Gen2, an upgrade to the current neutrino telescope IceCube. READ MORE

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

    University essay from Lunds universitet/Matematik LTH

    Author : Johan Liljegren; Pontus Nordqvist; [2021]
    Keywords : 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;

    Abstract : 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. READ MORE

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

    University essay from Lunds universitet/Statistiska institutionen

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

    Abstract : 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. READ MORE

  4. 4. Instability of a bi-directional TiFGAN in unsupervised speech representation learning

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Matthaios Stylianidis; [2021]
    Keywords : ;

    Abstract : A major challenge in the application of machine learning in the speech domain is the unavailability of annotated data. Supervised machine learning techniques are highly dependent on the amount of labelled data and the quality of the labels. READ MORE

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

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Simon Westberg; [2021]
    Keywords : ;

    Abstract : 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. READ MORE