ML Anthology

Neuroevolution of a Multi-Generator GAN (Student Abstract)

Suraj Kumar Pandey
AAAI 2024 pp. 23608-23609
doi:10.1609/AAAI.V38I21.30493 /aaai/2024/pandey2024aaai-neuroevolution/

Abstract

Evolutionary Algorithms (EA) have been leveraged to tackle the challenges faced while using GANs such as mode collapse, vanishing gradient, latent space search, etc. However, the existing techniques of using EA with GANs operate backpropagation and EA in isolation from each other, leaving ample room for further exploration. This paper creates a collaborative bridge between EA and GANs by exploring a neuroevolution method for utilising both EA and backpropagation-based optimisation, simultaneously, for a multi-generator GAN architecture. Experiments conducted using a standard dataset with variants of the proposed method highlight the towering impact of each of the components involved in the proposed method.

PDF AAAI Semantic Scholar

Cite

Text

Pandey. "Neuroevolution of a Multi-Generator GAN (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024. doi:10.1609/AAAI.V38I21.30493

Markdown

[Pandey. "Neuroevolution of a Multi-Generator GAN (Student Abstract)." AAAI Conference on Artificial Intelligence, 2024.](https://mlanthology.org/aaai/2024/pandey2024aaai-neuroevolution/) doi:10.1609/AAAI.V38I21.30493

BibTeX

@inproceedings{pandey2024aaai-neuroevolution,
  title     = {{Neuroevolution of a Multi-Generator GAN (Student Abstract)}},
  author    = {Pandey, Suraj Kumar},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {23608-23609},
  doi       = {10.1609/AAAI.V38I21.30493},
  url       = {https://mlanthology.org/aaai/2024/pandey2024aaai-neuroevolution/}
}