Eigenspace Separation of Autocorrelation Memory Matrices for Capacity Expansion

New autocorrelation memory matrices which realize eigenspace separation are proposed from the geometrical viewpoint over association dynamics. These memorization methods realize narrower distributions of eigenvalues and remove self-connections in a natural way. As a result, stable memory patterns and large basins of attraction are achieved without iterative learning. Modification of recalling dynamics for the new memory matrices is discussed based on the existing modified dynamics to attain even more memory capacity. Copyright 1997 Elsevier Science Ltd.

[1]  Toshiki Kindo.  A geometrical analysis of the dynamics of associative memory , 1997 .

[2]  Tomoki Fukai,et al.  Statistical mechanics of attractor neural networks and self-consistent signal-to-noise analysis : analog neural networks with nonmonotonic transfer functions and enhancement of the storage capacity(New Developments in Statistical Physics Similarities in Diversities,YITP Workshop) , 1993 .

[3]  J. Fontanari,et al.  Retrieval via non-equilibrium states in neural networks , 1988 .

[4]  Y. Attikiouzel,et al.  Hopfield networks as discrete dynamical systems , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

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

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

[7]  E. Gardner.  Structure of metastable states in the Hopfield model , 1986 .

[8]  Mahesan Niranjan,et al.  A theoretical investigation into the performance of the Hopfield model , 1990, IEEE Trans. Neural Networks.

[9]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[10]  Masahiko Morita,et al.  Capacity of associative memory using a nonmonotonic neuron model , 1993, Neural Networks.

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

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

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

[14]  Sompolinsky,et al.  Spin-glass models of neural networks. , 1985, Physical review. A, General physics.

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