A Continuous-Time Model of Autoassociative Neural Memories Utilizing the Noise-Subspace Dynamics

This paper presents a continuous-time model of Autoassociative Neural Memories (ANMs) which correspond to a modified version of pseudoinverse-type ANMs. This ANM model is derived from minimizing the energy function for a modular neural network. Through the eigendecomposition of the connection matrix, we show that the dynamical properties of the ANM are qualitatively different in the two state subspaces: a pattern-subspace and a noise-subspace. The proposed ANM has a distinctive feature in the noise-subspace dynamics. The size of basins of attraction can be varied by controlling the contribution of the noise-subspace dynamics to the whole network. The first simulation confirms this attractive feature. In the second simulation, we investigate the performance robustness of the ANM for several kinds of correlated pattern sets. These simulation results confirm the usefulness of the proposed ANM.

[1]  Kazuyoshi Tsutsumi,et al.  An artificial modular neural network and its basic dynamical characteristics , 1998, Biological Cybernetics.

[2]  Mohamad H. Hassoun,et al.  High Performance Recording Algorithm For Hopfield Model Associative Memories , 1989 .

[3]  K. Tsutsumi,et al.  Cross-coupled Hopfield nets via generalized-delta-rule-based internetworks , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[4]  Kazuyoshi Tsutsumi,et al.  Higher degree error backpropagation in cross-coupled Hopfield nets , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[5]  Toshiki Kindo,et al.  A Geometrical Analysis of Associative Memory , 1998, Neural Networks.

[6]  Kazushi Ikeda.  A Spurious-Memory Free Associative Memory System , 1996 .

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

[8]  Dmitry O. Gorodnichy,et al.  Increasing Attraction of Pseudo-Inverse Autoassociative Networks , 1997, Neural Processing Letters.

[9]  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.

[10]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[11]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[12]  D P Casasent,et al.  Ho-Kashyap optical associative processors. , 1990, Applied optics.

[13]  R. L. Kashyap,et al.  An Algorithm for Linear Inequalities and its Applications , 1965, IEEE Trans. Electron. Comput..

[14]  S.-I. Amari,et al.  Neural theory of association and concept-formation , 1977, Biological Cybernetics.

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

[16]  Kazuyoshi Tsutsumi,et al.  Association performance of cross-coupled Hopfield nets for correlated patterns , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).