论文信息 - A synthesis procedure for Hopfield's continuous-time associative memory

A synthesis procedure for Hopfield's continuous-time associative memory

A new technique is presented for designing associative memories to be implemented by Hopfield neural networks. This technique guarantees that each desired memory is stored and is attractive. The procedure also guarantees that the resulting network can be implemented, a requirement often overlooked by other methods. This synthetic procedure does not require a symmetric interconnection matrix; instead, stability is guaranteed by use of the results presented by A.N. Michel et al. (1989). Two examples are presented that demonstrate the synthesis procedure's storage ability and flexibility. >

Anthony N. Michel | Jay A. Farrell | J. Farrell | A. Michel

[1] Personnaz,et al. Collective computational properties of neural networks: New learning mechanisms. , 1986, Physical review. A, General physics.

[2] Eric Goles,et al. Lyapunov function for parallel neural networks , 1987 .

[3] I. Guyon,et al. Information storage and retrieval in spin-glass like neural networks , 1985 .

[5] Wolfgang Porod,et al. Qualitative analysis and synthesis of a class of neural networks , 1988 .

[6] J J Hopfield,et al. Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[7] Wolfgang Porod,et al. Analysis and synthesis of a class of neural networks: variable structure systems with infinite grain , 1989 .

[8] 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.

[9] John J. Hopfield,et al. Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[10] J. Farrell,et al. Qualitative analysis of neural networks , 1989 .