Abstract
This paper presents initial results of Generalized Compressed Network Search (GCNS), a method for automatically identifying the important frequencies for neural networks encoded as a set of Fourier-type coeficients (i.e. \compressed" networks [2]). GCNS achieves better compression than our previous approach, and promises better generalization capabilities. Results for a high-dimensional Octopus arm control problem show that a high fitness 3680-weight network can be encoded using less than 10 coeficients, using the frequencies identified by GCNS. Copyright is held by the author/owner(s).
| Original language | English (US) |
|---|---|
| Title of host publication | GECCO'12 - Proceedings of the 14th International Conference on Genetic and Evolutionary Computation Companion |
| Publisher | Association for Computing Machinery |
| Pages | 647-648 |
| Number of pages | 2 |
| ISBN (Print) | 9781450311786 |
| DOIs | |
| State | Published - Jan 1 2012 |
| Externally published | Yes |