Cooperative Coevolutionary Spatial Topologies for Autoencoder Training
Name
3638529.3654127.pdf
Size
1.49 MB
Format
Adobe PDF
Checksum (MD5)
27f649a5b41bb2468332f168724a7757
Author(s)
Hemberg, Erik
O'Reilly, Una-May
Toutouh, Jamal
Date Issued
July 14, 2024
Publisher
ACM|Genetic and Evolutionary Computation Conference
Citation
Hemberg, Erik, O'Reilly, Una-May and Toutouh, Jamal. 2024. "Cooperative Coevolutionary Spatial Topologies for Autoencoder Training."
Version
Final published version
Abstract
Training autoencoders is non-trivial. Convergence to the identity function or overfitting are common pitfalls. Population based algorithms like coevolutionary algorithms can provide diversity. To more robustly train autoencoders, we introduce a novel cooperative coevolutionary algorithm that exploits a spatial topology. We investigate the impact of algorithm parameters and design choices on the performance. On a simple tunable benchmark problem we observe that the performance can be improved over that of an conventionally trained autoencoder. However, the training convergence can be slow, despite the final model performance being competitive with a conventional autoencoder.
Description
GECCO ’24, July 14–18, 2024, Melbourne, VIC, Australia
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3638529.3654127
