Bidirectional Retrieval from Associative Memory

Similarity based fault tolerant retrieval in neural associative memories (NAM) has not lead to wiedespread applications. A drawback of the efficient Willshaw model for sparse patterns [Ste61, WBLH69], is that the high asymptotic information capacity is of little practical use because of high cross talk noise arising in the retrieval for finite sizes. Here a new bidirectional iterative retrieval method for the Willshaw model is presented, called crosswise bidirectional (CB) retrieval, providing enhanced performance. We discuss its asymptotic capacity limit, analyze the first step, and compare it in experiments with the Willshaw model. Applying the very efficient CB memory model either in information retrieval systems or as a functional model for reciprocal cortico-cortical pathways requires more than robustness against random noise in the input: Our experiments show also the segmentation ability of CB-retrieval with addresses containing the superposition of pattens, provided even at high memory load.

[1]  Günther Palm,et al.  Iterative retrieval of sparsely coded associative memory patterns , 1996, Neural Networks.

[2]  B Kosko,et al.  Adaptive bidirectional associative memories. , 1987, Applied optics.

[3]  James M. Bower,et al.  Computational Neuroscience: Trends in Research , 1996 .

[4]  Andrew Chi-Sing Leung,et al.  Stability and statistical properties of second-order bidirectional associative memory , 1997, IEEE Trans. Neural Networks.

[5]  M. A. Tainsh.  Intelligence, Information Processing and Analogical Reasoning: The Componential Analysis of Human Abilities. By Robert J. Sternberg. (New York: John Wiley & Sons Ltd., 1977.) [Pp. xi + 348.] £14-20. , 1980 .

[6]  A. R. Gardner-Medwin.  The recall of events through the learning of associations between their parts , 1976, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[7]  Stephen K. Reed,et al.  Book reviewIntelligence, information processing, and analogical reasoning: by Robert J. Sternberg. Hillsdale, New Jersey: Lawrence Erlbaum Associates, 1977. xi + 348 pp. $19.95 , 1977 .

[8]  John Robinson,et al.  Statistical analysis of the dynamics of a sparse associative memory , 1992, Neural Networks.

[9]  Günther Palm,et al.  Improved bidirectional retrieval of sparse patterns stored by Hebbian learning , 1999, Neural Networks.

[10]  Stability , 1973 .

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

[12]  Friedrich Gebhardt.  Text signatures by superimposed coding of letter triplets and quadruplets , 1987, Inf. Syst..

[13]  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.

[14]  David J. Willshaw,et al.  Improving recall from an associative memory , 1995, Biological Cybernetics.

[15]  Andrew Chi-Sing Leung,et al.  Stability, capacity, and statistical dynamics of second-order bidirectional associative memory , 1995, IEEE Trans. Syst. Man Cybern..

[16]  Intelligence , 1836, The Medico-chirurgical review.

[17]  Günther Palm,et al.  Bidirectional completion of cell assemblies in the cortex , 1998 .

[18]  Jose B. Cruz,et al.  Two coding strategies for bidirectional associative memory , 1990, IEEE Trans. Neural Networks.