Evolving neural networks in compressed weight space

  title={Evolving neural networks in compressed weight space},
  author={Jan Koutn{\'i}k and Faustino J. Gomez and J{\"u}rgen Schmidhuber},
We propose a new indirect encoding scheme for neural networks in which the weight matrices are represented in the frequency domain by sets Fourier coefficients. This scheme exploits spatial regularities in the matrix to reduce the dimensionality of the representation by ignoring high-frequency coefficients, as is done in lossy image compression. We compare the efficiency of searching in this "compressed" network space to searching in the space of directly encoded networks, using the CoSyNE… CONTINUE READING
Highly Cited
This paper has 64 citations. REVIEW CITATIONS

8 Figures & Tables



Citations per Year

65 Citations

Semantic Scholar estimates that this publication has 65 citations based on the available data.

See our FAQ for additional information.