论文信息 - Associative Memory Networks and Sparse Similarity Preserving Codes

Associative Memory Networks and Sparse Similarity Preserving Codes

This paper addresses the following main topics: Definition of the associative memory tasks, auto-association and hetero-association. Use of neural networks and local learning rules for the realization of associative memory. Derivation of the information capacity as an evaluation criterion. Comparision and optimization of local learning rules for associative memory. Sparse, distributed, similarity preserving data representation.

Günther Palm | Friedhelm Schwenker | Friedrich T. Sommer

[1] H. C. LONGUET-HIGGINS,et al. Non-Holographic Associative Memory , 1969, Nature.

[2] W. Little. The existence of persistent states in the brain , 1974 .

[3] D. O. Hebb,et al. The organization of behavior , 1988 .

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

[5] Günther Palm,et al. Information capacity in recurrent McCulloch-Pitts networks with sparsely coded memory states , 1992 .

[6] Günther Palm,et al. Local Synaptic Rules with Maximal Information Storage Capacity , 1988 .

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

[8] Örjan Ekeberg. Robust Dictionary Lookup Using Associative Networks , 1988, Int. J. Man Mach. Stud..

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

[10] Günther Palm,et al. On the Information Storage Capacity of Local Learning Rules , 1992, Neural Computation.

[11] 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.