Generalized compressed network search

Rupesh Kumar Srivastava, Jürgen Schmidhuber, Faustino Gomez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations


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 languageEnglish (US)
Title of host publicationGECCO'12 - Proceedings of the 14th International Conference on Genetic and Evolutionary Computation Companion
PublisherAssociation for Computing Machinery
Number of pages2
ISBN (Print)9781450311786
StatePublished - Jan 1 2012
Externally publishedYes


Dive into the research topics of 'Generalized compressed network search'. Together they form a unique fingerprint.

Cite this