Implementation of Hopfield Associative Memory with Evolutionary Algorithm and MC-Adaptation Rule for Pattern Storage
This paper describes the strategy for implementation of Hopfield neural network as associative memory with the genetic algorithm and the Monte Carlo-(MC-) adaptation rule for pattern storage. In the Hopfield type neural networks of associative memory, the appropriate arrangement of synaptic weights provides an associative memory feature in the network. The fixed-point stable state of this model represents the appropriate storage of the input patterns. The aim is to obtain the optimal weight matrix for efficient recalling of any prototype input pattern. The performance of the Hopfield neural network, especially the capacity and the quality of the recalling, can be greatly improved by making use of genetic algorithm and MC-adaptation rule. The experiments consider a neural network trained with multiple numbers of patterns using the Hebbian learning rule. In most cases, the recalling of patterns using genetic algorithm with MC-adaptation rule seems to give better results than the conventional hebbian rule, MC-adaptation rule and simple genetic algorithm recalling techniques.
KeywordsHopfield neural network Genetic algorithm Monte-Carlo adaptation rule Pattern association
Unable to display preview. Download preview PDF.
- 5.Haykin, S.: Neural Networks: A Comprehensive Foundation, ch. 14, p. 664. Prentice Hall, Upper Saddle River (1985)Google Scholar
- 7.Zhao, H.: Designing Asymmetric Neural Networks with Associative Memory. Physical Review 70(6), 066137-4 (2004)Google Scholar
- 9.Amit, D.J.: Mean-field Ising Model and Low Rates in Neural Networks. In: Proceedings of the International Conference on Statistical Physics, Seoul, Korea, June 5-7, pp. 1–10 (1997)Google Scholar
- 10.Imada, A., Araki, K.: Genetic Algorithm Enlarges the Capacity of Associative Memory. In: Proc. of the Sixth International Conf. on Genetic Algorithms, pp. 413–420 (1995)Google Scholar
- 13.Jin, T., Zhao, H.: Pattern Recognition using Asymmetric Attractor Neural Networks. Phys. Rev. E 72(6), 066111-7 (2005)Google Scholar
- 16.Hebb, D.: The Organization of Behaviour. In: A Neuropsychological Theory. Wiley, New York (1949)Google Scholar
- 20.Zhao, H., Jin, T.: A Global Algorithm for Training Multilayer Neural Networks, arXiv: physics/0607046 (2006)Google Scholar
- 21.Amari, S.: Learning and Statistical Inference. In: Arbib, M.A. (ed.) The Handbook of Brain Theory and Neural Networks, pp. 522–526. MIT Press, Cambridge (1993)Google Scholar