Abstract
This paper addresses the problem of automatically obtaining primitives of the models an evolutionary cognitive mechanism is producing for a robot through its real time interaction with the world. The models are instantiated as Artificial Neural Networks (ANNs) and the objective is to obtain ANNs that cooperate in the process of modelling complex functions. An algorithm where the combination of networks takes place at the phenotypic or functional level is proposed. Thus, a population of networks that are automatically classified into different species depending on the performance of their phenotype is evolved, and individuals from each species cooperate forming a group to obtain a complex output. The components that make up the groups are basic ANNs (primitives) and may be reused in other modelling processes as seeds or combined to generate new solutions. The parameter that reflects the difference between ANNs is their affinity vector, the value which is automatically created and modified for each ANN through a competition based clustering process within the evolutionary process. The main objective of this approach is to explore one path to gradually model complex functions similar to those that arise when obtaining environment or internal models within robotic cognitive systems.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bellas F, Becerra JA, Duro RJ (2006a) Construction of a memory management system in an on-line learning mechanism. In: ESANN 2006 Proceedings book, pp 95–100
Bellas F, Faiña A, Prieto A, Duro RJ (2006b) Adaptive learning application of the MDB evolutionary cognitive architecture in physical agents, LNCS 4095, pp 434–445
Bellas F, Becerra JA, Duro RJ (2009) Using promoters and functional introns in genetic algorithms for neuroevolutionary learning in non-stationary problems. Neurocomputing 72:2134–2145
Coello C, Van Veldhuizen D, Lamont G (2002) Evolutionary algorithms for solving multi-objective problems. Kluwer, Dordrecht
Darwen P, Yao X (1997) Speciation as automatic categorical modularization. IEEE Trans Evol Comput 1(2):101–108
Deb K, Goldberg DE (1989) An investigation of niche and species-formation in genetic function optimization. In: Proceedings of 3rd International Conference Genetic Algorithms, pp 42–50
DellaCioppa A, DeStefano C, Marcelli A (2004) On the role of population size and niche radius in fitness sharing. IEEE Trans Evol Comput 8(6):580–592
Duro RJ, Santos J, Bellas F, Lamas A (2000) On line darwinist cognitive mechanism for an artificial organism. In: Proceedings supplement book SAB2000, pp 215–224
García-Pedrajas N (2009) Constructing ensembles of classifiers by means of weighted instance selection. IEEE Trans Neural Netw 20(2):258–277
García-Pedrajas N, Hervás-Martínez C, Muñoz-Pérez J (2003) COVNET: a cooperative coevolutionary model for evolving artificial neural networks. IEEE Trans Neural Netw 14(3):575–596
García-Pedrajas N, Hervás-Martínez C, Ortiz-Boyer D (2005) Cooperative coevolution of artificial neural network ensembles for pattern classification. IEEE Trans Evol Comput 9(3):271–302
Goldberg D, Richardson J (1987) Genetic algorithms with sharing for multimodal function optimization. In: Proceedings of 2nd international conference on genetic algorithms, pp 41–49
Khare VR, Yao X, Sendhoff B, Jin Y, Wersing H (2005), Co-evolutionary modular neural networks for automatic problem decomposition. In: Congress on evolutionary computation (CEC). IEEE Press, pp 2691–2698
Khare VR, Yao X, Sendhoff B (2006) Multi-network evolutionary systems and automatic decomposition of complex problems. Int J Gen Syst 35(3):259–274
Liu Y, Yao X, Higuchi T (2000) Evolutionary ensembles with negative correlation learning. IEEE Trans Evol Comput 4(4):380–387
Moriarty DE, Miikkulainen R (1998) Forming neural networks through efficient and adaptive coevolution. Evol Comput 4(5):373–399
Nguyen M, Abbass HA, McKay R (2008) Analysis of CCME: coevolutionary dynamics, automatic problem decomposition, and regularization. IEEE Trans Syst Man Cybern C Appl Rev 38(1):100–109
Opitz DW, Shavlik JW (1996) Actively searching for an effective neural network ensemble. Connection Sci 8(3):337–353
Sharkey AJC (1996) On combining artificial neural nets connection. Science 8(3 & 4):299–314
Smalz R, Conrad M (1994) Combining evolution with credit apportionment: a new learning algorithm for neural nets. Neural Netw 7(2):341–351
Acknowledgments
This work was funded by the Xunta de Galicia through project 09DPI012166PR supported by European Regional Development Funds.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Duro, R.J., Bellas, F., Caamaño, P. et al. Automatic model decomposition and reuse in an evolutionary cognitive mechanism. Evolving Systems 1, 129–141 (2010). https://doi.org/10.1007/s12530-010-9012-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12530-010-9012-z