Description

Generative Adversarial Networks are designed, in theory, to replicate the distribution of the data they are trained on. With real-world limitations, such as finite network capacity and training set size,

Generative Adversarial Networks are designed, in theory, to replicate the distribution of the data they are trained on. With real-world limitations, such as finite network capacity and training set size, they inevitably suffer a yet unavoidable technical failure: mode collapse. GAN-generated data is not nearly as diverse as the real-world data the network is trained on; this work shows that this effect is especially drastic when the training data is highly non-uniform.

11.17 MB application/pdf

Download count: 0

Details

Contributors
Date Created
  • 2020
Resource Type
  • Text
  • Collections this item is in
    Note
    • Masters Thesis Computer Science 2020

    Machine-readable links