Encouraging GAN diversity via evolutionary computing
Author(s)Woldu, Kifle(Kifle H.)
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
MetadataShow full item record
Generative Adversarial Networks(GANs) have become very popular for their use in generating high quality images. Unfortunately, GANs also suffer from training instability, making them hard to use in practice. In this thesis, we investigate a specific form of instability called mode collapse, where the model only learns a portion of the distribution. We augment standard GANs with approaches from evolutionary computing and find the augmentation does improve diversity substantially. Additionally, we develop new evolutionary models that further encourage diversity, along with an accompanying modular framework.
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020Cataloged from the official PDF of thesis.Includes bibliographical references (pages 37-38).
DepartmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology
Electrical Engineering and Computer Science.