Title :
Evolution of a dynamical modular neural network and its application to associative memories
Author :
Ozawa, Seiichi ; Tsutumi, Kousuke ; Baba, Norio
Author_Institution :
Dept. of Inf. Sci., Osaka Kyoiku Univ., Japan
Abstract :
This paper presents an evolutionary approach to architecture design of dynamical modular neural networks. As one of the modular neural networks, we adopt Cross-Coupled Hopfield Nets (CCHN) in which Hopfield networks are coupled to each other. The architecture of CCHN is represented by some structural parameters such as the number of modules, the numbers of module units, module connectivity, and so forth. In this paper, these structural parameters are treated as the pheno-type of an individual, and a suitable modular architecture is searched by using genetic algorithms. To verify the usefulness of the proposed architecture design algorithm we apply CCHN to associative memories
Keywords :
Hopfield neural nets; content-addressable storage; genetic algorithms; neural net architecture; search problems; Cross-Coupled Hopfield Nets; associative memories; dynamical modular neural network; evolutionary approach; genetic algorithms; neural net architecture; search; structural parameters; Algorithm design and analysis; Artificial neural networks; Associative memory; Feedforward neural networks; Genetic algorithms; Hopfield neural networks; Information processing; Intelligent systems; Multi-layer neural network; Neural networks;
Conference_Titel :
Knowledge-Based Intelligent Information Engineering Systems, 1999. Third International Conference
Conference_Location :
Adelaide, SA
Print_ISBN :
0-7803-5578-4
DOI :
10.1109/KES.1999.820140