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 Fourier-type coefficients (i.e. “compressed” networks [7]). GCNS is a general search procedure in this coefficient space – both the number of frequencies and their value are automatically determined by employing the use of variable-length chromosomes, inspired by messy genetic algorithms. The method achieves better compression than our previous approach, and promises improved generalization for evolved controllers. Results for a high-dimensional Octopus arm control problem show that a high fitness 3680-weight network can be encoded using less than 10 coefficients using the frequencies identified by GCNS.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with analog genetic encoding. In: PPSN, pp. 671–680 (2006)
Goldberg, D., Korb, B., Deb, K.: Messy genetic algorithms: Motivation, analysis, and first results. Complex systems 3(5), 493–530 (1989)
Goldberg, D.E., Deb, K., Kargupta, H., Harik, G.: Rapid, accurate optimization of difficult problems using fast messy genetic algorithms. In: Proc. of the Fifth International Conference on Genetic Algorithms, pp. 56–64. Morgan Kaufmann (1993)
Gomez, F., Koutník, J., Schmidhuber, J.: Compressed Network Complexity Search. In: Coello Coello, C.A., et al. (eds.) PPSN 2012, Part I. LNCS, vol. 7491, pp. 316–326. Springer, Heidelberg (2012)
Gruau, F.: Cellular encoding of genetic neural networks. Technical Report RR-92-21, Ecole Normale Superieure de Lyon, Institut IMAG, Lyon, France (1992)
Kitano, H.: Designing neural networks using genetic algorithms with graph generation system. Complex Systems 4, 461–476 (1990)
Koutník, J., Gomez, F., Schmidhuber, J.: Evolving neural networks in compressed weight space. In: Proc. of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 619–626. ACM (2010)
Koutník, J., Gomez, F., Schmidhuber, J.: Searching for minimal neural networks in fourier space. In: Proc. of the 4th Conf. on Artificial General Intelligence (2010)
Schmidhuber, J.: Discovering neural nets with low Kolmogorov complexity and high generalization capability. Neural Networks 10(5), 857–873 (1997)
Yekutieli, Y., Sagiv-Zohar, R., Aharonov, R., Engel, Y., Hochner, B., Flash, T.: Dynamic model of the octopus arm. I. Biomechanics of the octopus reaching movement. Journal of Neurophysiology 94(2), 1443–1458 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Srivastava, R.K., Schmidhuber, J., Gomez, F. (2012). Generalized Compressed Network Search. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds) Parallel Problem Solving from Nature - PPSN XII. PPSN 2012. Lecture Notes in Computer Science, vol 7491. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32937-1_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-32937-1_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32936-4
Online ISBN: 978-3-642-32937-1
eBook Packages: Computer ScienceComputer Science (R0)