Encouraging GAN diversity via evolutionary computing
Name
1193031976-MIT.pdf
Size
2.08 MB
Format
Adobe PDF
Checksum (MD5)
75659adf2ca32d96cfee2375a99b7fc5
Author(s)
Woldu, Kifle(Kifle H.)
Advisor(s)
Erik Hemberg.
Date Issued
2020
Publisher
Massachusetts Institute of Technology
Abstract
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[5]. 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.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020
Cataloged from the official PDF of thesis.
Includes bibliographical references (pages 37-38).
Subjects
Electrical Engineering and Computer Science.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided.
Persistent DSpace Link
