Abstract
A locally iterative learning (LIL) rule is adapted to a model of the associative memory based on the evolving recurrent-type neural networks composed of growing neurons. There exist extremely different scale parameters of time, the individual learning time and the generation in evolution. This model allows us definite investigation on the interaction between learning and evolution. And the reinforcement of the robustness against the noise is also achieved in the evolutional scheme.
Similar content being viewed by others
References
X. Yao. Evolutionary artificial neural networks,Int. J. Neural Systems, vol. 4, pp. 203–222, 1993.
J. Branke. Evolutionary algorithms for neural network design and training, inProc. of the 1st Nordic Workshop on Genetic Algorithms and its Applications, Vaasa, Finland, 1995.
Sh. Fujita, H. Nishimura. An evolutionary approach to associative memory in recurrent neural networks,Neural Processing Letters, vol. 1, pp. 9–13, 1994.
S. Nolfi, D. Parisi. Growing neural networks,Technical Report PCIA-91-15, Institute of Psychology CNR. —Rome, 1991.
S. Nolfi, O. Miglino, D. Parisi. Phenotypic plasticity in evolving neural networks,Technical Report, PCIA-94-05, Institute of Psychology CNR. —Rome, 1994.
F. Rosenblatt.Principles of Neurodynamics, Spartan, New York, 1962.
B. Müller, J. Reinhardt.Neural Networks: An Introduction, Springer-Verlag, 1990.
S. Diederich, M. Opper. Learning of correlated patterns in spin-glass networks by local learning rules,Phys. Rev. Lett., vol. 58, pp. 949–952, 1987.
J.M. Baldwin. A new factor in evolution,American Naturalist, vol. 30, pp. 441–451, 1896.
G. Hinton, S. Nowlan. How learning can guide evolution,Complex Systems, vol. 1, pp. 495–502, 1987.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Fujita, S., Nishimura, H. Evolving neural networks with iterative learning scheme for associative memory. Neural Process Lett 2, 1–5 (1995). https://doi.org/10.1007/BF02279930
Issue Date:
DOI: https://doi.org/10.1007/BF02279930