Title :
The estimation of cross-coupled Hopfield nets as an interactive modular neural network
Author :
Ozawa, S. ; Tsutsumi, K. ; Baba, N.
Author_Institution :
Dept. of Inf., Osaka Kyoiku Univ., Ikeda, Japan
fDate :
27 Jun-2 Jul 1994
Abstract :
This paper describes the effects on the association performance of cross-coupled Hopfield nets (CCHN) due to the increase in the number of modules M, in order to clarify the usefulness as an interactive modular neural network. The association performance of a cross-coupled Hopfield net with many-to-many mapping internetworks (CCHN-MMMI), which is an extended version of CCHN is investigated through computer simulations. The simulation results show that the performance of CCHN-MMMI is greatly improved as compared with that of a conventional Hopfield network (HN) as long as M is not too large. However, in our simulation, the performance of CCHN-MMMI with M⩾16 is worse than or equal to that of HN. In order to clarify the factors on its performance deterioration, the features-of average activities in modules and interactions are separately investigated. As a result, we clarify three factors on the deterioration and suggest some approaches to solve them
Keywords :
Hopfield neural nets; interactive systems; modules; performance evaluation; average energy value; cross-coupled Hopfield nets; interactive modular neural network; many-to-many mapping internetworks; performance deterioration; Artificial neural networks; Computational modeling; Computer simulation; Hopfield neural networks; IP networks; Information processing; Information science; Internet; Neural networks; Resonance;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374479
