BayesBiGAN and GANify - Research and a Developer Tool for Generative Adversarial Networks.

Dinjian, Daniel.


  • This thesis concerns the current state of Generative Adversarial Networks (GANs) in the field of Machine Learning. The first part of the work combines the BayesGAN and the BiGAN models to create the Bayesian Bidirectional GAN (BayesBiGAN). The BayesBiGAN uses the BayesGAN's MCMC training method to sample from posteriors over the generator, discriminator, and the BiGAN encoder. This model ... read more
This object is in collection Creator department Thesis Type Genre Permanent URL
To Cite:
TARC Citation Guide    EndNote