For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Retrieval Property of Associative Memory Based on Inverse Function Delayed Neural Networks
Hongge LI Yoshihiro HAYAKAWA Koji NAKAJIMA
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2005/08/01
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Nonlinear Problems
associative memory, inverse function delayed model, retrieval dynamics, basin of attraction, negative resistance,
Full Text: PDF>>
Self-connection can enlarge the memory capacity of an associative memory based on the neural network. However, the basin size of the embedded memory state shrinks. The problem of basin size is related to undesirable stable states which are spurious. If we can destabilize these spurious states, we expect to improve the basin size. The inverse function delayed (ID) model, which includes the Bonhoeffer-van der Pol (BVP) model, has negative resistance in its dynamics. The negative resistance of the ID model can destabilize the equilibrium states on certain regions of the conventional neural network. Therefore, the associative memory based on the ID model, which has self-connection in order to enlarge the memory capacity, has the possibility to improve the basin size of the network. In this paper, we examine the fundamental characteristics of an associative memory based on the ID model by numerical simulation and show the improvement of performance compared with the conventional neural network.