Abstract
The framework of neuroevolution (NE) provides a way of finding appropriate structures as well as connection weights of artificial neural networks. However, the conventional NE approach of directly coding each connection weight by a gene is severely limited in its scalability and evolvability. In this study, we propose a novel indirect coding approach in which a phenotypical network develops from the genes encoding multiple subnetwork modules. Each gene encodes a subnetwork consisting of the input, hidden, and output nodes and connections between them. A connection can be a real weight or a pointer to another subnetwork. The structure of the network evolves by inserting new connection weights or subnetworks, merging two subnetworks as a higher-level subnetwork, or changing the existing connections. We investigated the evolutionary process of the network structure using the task of double pole balancing. We confirmed that the proposed method by the modular developmental rule can produce a wide variety of network architectures and that evolution can trim them down to the most appropriate ones required by the task.
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.
References
Miikkulainen, R.: Evolving neural networks. In: Procs. of Genetic and Evolutionary Computation Conference (GECCO 2007), pp. 3415–3434. ACM, New York (2007)
Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evolutionary Intelligence 1(1), 47–62 (2008)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)
Reisinger, J., Miikkulainen, R.: Acquiring evolvability through adaptive representations. In: Procs. of Genetic and Evolutionary Computation Conference (GECCO 2007), pp. 1045–1052. ACM, New York (2007)
Nolfi, S., Parisi, D.: “genotypes” for neural networks. In: The handbook of brain theory and neural networks table of contents, pp. 431–434 (1998)
Seys, C.W., Beer, R.D.: Effect of encoding on the evolvability of an embodied neural network. In: GECCO 2006 Workshop Procs., Workshop on Complexity through Development and Self-Organizing Representations (CODESOAR) (2006)
Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with analog genetic encoding. In: Procs. of the 9th International Conference on Parallel Problem Solving from Nature (PPSN IX). LNCS, vol. 9, pp. 671–680. Springer, Heidelberg (2006)
Mattiussi, C., Floreano, D.: Analog genetic encoding for the evolution of circuits and networks. IEEE Transactions on Evolutionary Computation 11(5), 596–607 (2007)
Gauci, J., Stanley, K.O.: A case study on the critical role of geometric regularity in machine learning. In: Procs. of the Twenty-Third AAAI Conference on Artificial Intelligence (AAAI 2008). AAAI Press, Menlo Park (2008) (to appear)
Kirschner, M., Gerhart, J.: Evolvability. Proceedings of the National Academy of Sciences (PNAS) 95(15), 8420–8427 (1998)
Raff, R.A., Sly, B.J.: Modularity and dissociation in the evolution of gene expression territories in development. Evolution & Development 2(2), 102–113 (2000)
Gruau, F.: Automatic definition of modular neural networks. Adaptive Behaviour 3(2), 151–183 (1995)
Reisinger, J., Stanley, K.O., Miikkulainen, R.: Evolving reusable neural modules. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3103, pp. 69–81. Springer, Heidelberg (2004)
Walker, J.A., Miller, J.F.: Automatic acquisition, evolution and re-use of modules in cartesian genetic programming. IEEE Transactions on Evolutionary Computation 12(4) (August 2008)
Schaffer, J.D., Whitley, D., Eshelman, L.J.: Combinations of genetic algorithms and neural networks: a survey of the state of the art. In: International workshop on Combinations of Genetic Algorithms and Neural Networks (COGANN 1992), pp. 1–37 (1992)
Radcliffe, N.J.: Forma analysis and random respectful recombination. In: Procs. of the Fourth International Conference on Genetic Algorithms, pp. 222–229. Morgan Kaufmann Publishers, San Francisco (1991)
Kassahun, Y.: Towards a Unified Approach to Learning and Adaptation. PhD thesis, Inst. f. Informatik u. Prakt. Math. der Christian-Albrechts-Universität zu Kiel (2006)
Siebel, N.T., Sommer, G.: Evolutionary reinforcement learning of artificial neural networks. International Journal of Hybrid Intelligent Systems 4(3), 171–183 (2007)
Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evolutionary Computation 9(2), 159–195 (2001)
Igel, C.: Neuroevolution for reinforcement learning using evolution strategies. In: Procs. of Congress on Evolutionary Computation (CEC 2003), vol. 4, pp. 2588–2595. IEEE Press, Los Alamitos (2003)
Gruau, F., Whitley, D., Pyeatt, L.: A comparison between cellular encoding and direct encoding for genetic neural networks. In: Genetic Programming 1996: Procs. of the First Annual Conference, pp. 81–89. MIT Press, Cambridge (1996)
Gomez, F., Schmidhuber, J., Miikkulainen, R.: Accelerated neural evolution through cooperatively coevolved synapses. The Journal of Machine Learning Research 9, 937–965 (2008)
Elfwing, S., Uchibe, E., Doya, K., Christensen, H.I.: Evolutionary development of hierarchical learning structures. IEEE Transactions on Evolutionary Computations 11(2), 249–264 (2007)
Elfwing, S., Uchibe, E., Doya, K., Christensen, H.I.: Darwinian embodied evolution of the learning ability for survival. Adaptive Behavior (to appear)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kamioka, T., Uchibe, E., Doya, K. (2009). NeuroEvolution Based on Reusable and Hierarchical Modular Representation. In: Köppen, M., Kasabov, N., Coghill, G. (eds) Advances in Neuro-Information Processing. ICONIP 2008. Lecture Notes in Computer Science, vol 5506. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02490-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-02490-0_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02489-4
Online ISBN: 978-3-642-02490-0
eBook Packages: Computer ScienceComputer Science (R0)