Retrieval property of associative memory with negative resistance

The 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 states. If we can destabilize these spurious states, we expect to improve the basin size. The inverse function delayed (ID) model which includes the BVP model has the negative resistance on its dynamics. The negative resistance of the ID model can destabilize the equilibrium states on some regions of conventional neural network. Hence, the associative memory based on the ID model has possibilities of improving the basin size of the network which has the self-connection in order to enlarge a memory capacity. In this paper, we show the improvement of performance compared with the conventional neural network by computer simulation.

[1]  Shun-ichi Amari,et al.  Statistical neurodynamics of associative memory , 1988, Neural Networks.

[2]  Kanter,et al.  Associative recall of memory without errors. , 1987, Physical review. A, General physics.

[3]  Anthony C. C. Coolen,et al.  Phase Diagram and Storage Capacity of Sequence-Storing Neural Networks , 1998, NIPS.

[4]  E. Gardner,et al.  Optimal basins of attraction in randomly sparse neural network models , 1989 .

[5]  H. Nishimori,et al.  Retrieval dynamics of associative memory of the Hopfield type , 1993 .

[6]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[7]  M. Okada,et al.  Transient dynamics for sequence processing neural networks , 2002, cond-mat/0202431.

[8]  Teuvo Kohonen,et al.  Correlation Matrix Memories , 1972, IEEE Transactions on Computers.

[9]  Sompolinsky,et al.  Storing infinite numbers of patterns in a spin-glass model of neural networks. , 1985, Physical review letters.

[10]  J Nagumo,et al.  [A model of associative memory]. , 1972, Iyo denshi to seitai kogaku. Japanese journal of medical electronics and biological engineering.

[11]  Masahiko Morita,et al.  Associative memory with nonmonotone dynamics , 1993, Neural Networks.

[12]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[13]  Yasuji Sawada,et al.  Associative memory network composed of neurons with hysteretic property , 1990, Neural Networks.

[14]  R. FitzHugh.  Impulses and Physiological States in Theoretical Models of Nerve Membrane. , 1961, Biophysical journal.

[15]  James A. Anderson,et al.  A simple neural network generating an interactive memory , 1972 .

[16]  M P Singh.  Hopfield model with self-coupling. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[17]  Koji Nakajima,et al.  Inverse Function Delayed Model for Optimization Problems , 2004, KES.

[18]  Kaoru Nakano,et al.  Associatron-A Model of Associative Memory , 1972, IEEE Trans. Syst. Man Cybern..

[19]  Margarita Kuzmina.  The recalling process dynamics of associative memory neural networks in macrodynamical approach , 1995, Neural Networks.