Abstract
In this paper, we investigate the associative memory in recurrent neural networks, based on the model of evolving neural networks proposed by Nolfi, Miglino and Parisi.Experimentally developed network has highly asymmetric synaptic weights and dilute connections, quite different from those of the Hopfield model.Some results on the effect of learning efficiency on the evolution are also presented.
Similar content being viewed by others
References
J.J. Hopfield. Neural Networks and Physical Systems with Emergent Collective Computational Abilities,Proc. Natl. Acad. Sci. USA, 79, pp.2554–2558, 1982.
B. Müller, J. Reinhardt.Neural Networks: An Introduction, Springer-Verlag, 1990.
J. Hertz, A. Krogh, R. Palmer.Introduction to the Theory of Neural Computation, Addison-Wesley, 1991.
J.H. Holland.Adaptation in Natural and Artificial Systems, University of Michigan Press, 1975.
X. Yao. Evolutionary Artificial Neural Networks,Int. J. Neural Systems, Vol. 4, pp.203–222, 1993.
H. Kitano. Designing Neural Networks using Genetic Algorithms with Graph Generation System,Complex Systems, 4, pp.461–476, 1990.
F. Gruau. Genetic synthesis of boolean neural networks with a cell rewriting developmental processes, in: D. Whitley, J.D. Schaffer eds.,Proc. of the Int. Workshop on Combinations of Genetic Algor. and Neural Networks (COGANN-92), IEEE Computer Society Press, Los Alamitos, CA, pp. 55–74, 1992.
S. Nolfi, D. Parisi. Growing Neural Networks,Technical Report PCIA-91-15, Institute of Psychology C.N.R.- Rome, 1991.
S. Nolfi, O. Miglino, D. Parisi. Phenotypic Plasticity in Evolving Neural Networks,Technical Report PCIA-94-05, Institute of Psychology C.N.R. - Rome, 1994.
G. Hinton, S. Nowlan. How Learning Can Guide Evolution,Complex Systems, 1, pp.495–502, 1987.
D. Ackley, H. Littman. Interactions between learning and evolution, in: C.G. Langsten, C. Taylor, J.D. Fanner, S. Rasmussen eds.,Artificial Life II, Addison-Wesley, pp.487–509, 1991.
G. Edelman.Neural Darwinism: The Theory of the Neuronal Group Selection, Basic Books, 1987.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Fujita, S., Nishimura, H. An evolutionary approach to associative memory in recurrent neural networks. Neural Process Lett 1, 9–13 (1994). https://doi.org/10.1007/BF02310936
Issue Date:
DOI: https://doi.org/10.1007/BF02310936