Abstract
Echo State Networks (ESN) have demonstrated their efficiency in supervised learning of time series: a ”reservoir” of neurons provide a set of dynamical systems that can be linearly combined to match the target dynamics, using a simple quadratic optimisation algorithm to tune the few free parameters. In an unsupervised learning context, however, another optimiser is needed. In this paper, an adaptive (1+1)-Evolution Strategy is used to optimise an ESN to tackle the ”flag” problem, a classical benchmark from multi-cellular artificial embryogeny: the genotype is the cell controller of a Continuous Cellular Automata, and the phenotype, the image that corresponds to the fixed-point of the resulting dynamical system, must match a given 2D pattern. This approach is able to provide excellent results with few evaluations, and favourably compares to that using the NEAT algorithm (a state-of-the-art neuro-evolution method) to evolve the cell controllers. Some characteristics of the fitness landscape of the ESN-based method are also investigated.
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
Angeline, P.J., Saunders, G.M., Pollack, J.P.: An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks 5(1), 54–65 (1994)
Ash, T.: Dynamic node creation in backpropagation networks. Connection Science 1(4), 365–375 (1989)
Auger, A., Hansen, N.: A restart cma evolution strategy with increasing population size. In: Proceedings of the IEEE Congress on Evolutionary Computation (CEC 2005), pp. 1769–1776 (2005)
Babinec, S.: Evolutionary optimization methods in echo state networks. In: 6th Czech-Slovak Workshop on Cognition and Artificial Life (2006)
Banzhaf, W.: On the dynamics of an artificial regulatory network. In: Banzhaf, W., Ziegler, J., Christaller, T., Dittrich, P., Kim, J.T. (eds.) ECAL 2003. LNCS (LNAI), vol. 2801, pp. 217–227. Springer, Heidelberg (2003)
Beyer, H.-G., Schwefel, H.-P.: Evolution strategies: A comprehensive introduction. Natural Computing: an international journal 1(1), 3–52 (2002)
D’Ambrosio, D.B., Stanley, K.O.: A novel generative encoding for exploiting neural network sensor and output geometry. In: Thierens, D., et al. (eds.) GECCO 2007, ACM Press, New York (2007)
Dematos, G., Boyd, M., Kermanshahi, B., Kohzadi, N., Kaastra, I.: Feedforward versus recurrent neural networks for forecasting monthly japanese yen exchange rates. Asia-Pacific Financial Markets 3(1), 59–75 (1996)
Devert, A., Bredeche, N., Schoenauer, M.: Robust multi-cellular developmental design. In: Thierens, D., et al. (eds.) GECCO 2007, ACM Press, New York (2007), http://hal.inria.fr/inria-00145336/en/
Durr, P., Mattiussi, C., Floreano, D.: Neuroevolution with analog genetic encoding. In: PPSN IX, pp. 671–680 (2006)
Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, Denver, vol. 2, pp. 524–532. Morgan Kaufmann, San Mateo (1990)
Federici, D., Downing, K.: Evolution and development of a multicellular organism: scalability, resilience, and neutral complexification. Artificial Life 12(3), 381–409 (2006)
Gomez, F., Miikkulainen, R.: Incremental evolution of complex general behavior. Technical Report AI96-248, 1 (1996)
Gordon, T.G.W., Bentley, P.J.: Bias and scalability in evolutionary development. In: GECCO 2005, pp. 83–90. ACM Press, New York (2005)
Gruau, F.: Genetic synthesis of modular neural networks. In: ICGA 1993, pp. 318–325. Morgan Kaufmann, San Francisco (1993)
Hastings, E., Guha, R., Stanley, K.O.: Neat particles: Design, representation, and animation of particle system effects. In: IEEE CIG 2007 (2007)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)
Husbands, P., Smith, T., Jakobi, N., O’Shea, M.: Better living through chemistry: Evolving gasnets for robot control. Connection Science 10(3-4), 185–210 (1998)
Jaeger, H.: The Echo State approach to analysing and training recurrent neural networks. Technical Report GMD Report 148, German National Research Center for Information Technology (2001)
Jaeger, H.: Short term memory in echo state network. Technical Report GMD Report 152, German National Research Center for Information Technology (2001)
Jaeger, H.: Tutorial on training recurrent neural networks. Technical report, GMD Report 159, Fraunhofer Institute AIS (2002)
Jaeger, H., Haas, H., Principe, J.C. (eds.): NIPS 2006 Workshop on Echo State Networks and Liquid State Machines (2006)
Kern, S., Müller, S.D., Hansen, N., Büche, D., Ocenasek, J., Koumoutsakos, P.: Learning probability distributions in continuous evolutionary algorithms: a comparative review. Natural Computing 3(1), 77–112 (2004)
Kohonen, T.: Self-Organizing Maps. Springer Series in Information Sciences, vol. 30. Springer, Berlin, Heidelberg (1997) (Second Extended Edition, 1997)
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.: Backpropagation applied to handwritten zip code recognition. Neural Computation 1(4), 541–551 (1989)
LeCun, Y., Denker, J.S., Solla, S., Howard, R.E., Jackel, L.D.: Optimal brain damage. In: Touretzky, D. (ed.) NIPS 1989, Morgan Kaufman, San Francisco (1990)
Miller, J.F.: Evolving a self-repairing, self-regulating, french flag organism. In: Deb, K., al., e. (eds.) GECCO 2004. LNCS, vol. 3102, pp. 129–139. Springer, Heidelberg (2004)
Moriarty, D.E.: Symbiotic evolution of neural networks in sequential decision tasks. Technical Report AI97-257, 1 (1997)
Ozturk, M.C., Xu, D., Principe, J.C.: Analysis and design of echo state networks. Neural Computation 19(1), 111–138 (2007)
Pearlmutter, B.A.: Gradient calculations for dynamic recurrent neural networks: A survey. IEEE Transactions on Neural Networks 6, 1212–1228 (1995)
Rechenberg, I.: Evolutionsstrategie: Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. Frommann-Holzboog, Stuttgart (1973)
Rumelhart, D.E., Hinton, G.E., McClelland, J.L.: Exploration in Parallel Distributed Processing. MIT Press, Cambridge (1988)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)
Whitley, D., Gruau, F., Pyeatt, L.: Cellular encoding applied to neurocontrol. In: ICGA 1995, pp. 460–467. Morgan Kaufman, San Francisco (1995)
Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 87(9), 1423–1447 (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Devert, A., Bredeche, N., Schoenauer, M. (2008). Unsupervised Learning of Echo State Networks: A Case Study in Artificial Embryogeny. In: Monmarché, N., Talbi, EG., Collet, P., Schoenauer, M., Lutton, E. (eds) Artificial Evolution. EA 2007. Lecture Notes in Computer Science, vol 4926. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-79305-2_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-79305-2_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-79304-5
Online ISBN: 978-3-540-79305-2
eBook Packages: Computer ScienceComputer Science (R0)