Abstract
This paper proposes multiport parallel and multidirectional intraconnected associative memories of outer product type with reduced interconnections. Some new reduced order memory architectures such as k-directional and k-port parallel memories are suggested. These architectures are, also, very suitable for implementation of spatio-temporal sequences and multiassociative memories. It is shown that in the proposed memory architectures, a substational reduction in interconnections is achieved if the actual length of original N-bit long vectors is subdivided into k sublengths. Using these sublengths, submemory matrices, T s or W s , are computed, which are then intraconnected to form k-port parallel or k-directional memories. The subdivisions of N-bit long vectors into k sublengths save \({\frac{(k-1)\times 100}{k}\% }\) of interconnections. It is shown, by means of an example, that more than 80% reduction in interconnections is achieved. Minimum limit in bits on k as well as maximum limit on subdivisions in k is determined. The topologies of reduced interconnectivity developed in this paper are symmetric in structure and can be used to scale up to larger systems. The underlying principal of construction, storage and retrieval processes of such associative memories has been analyzed. The effect of complexity of different levels of reduced interconnectivity on the quality of retrieval, signal to noise ratio, and storage capacity has been investigated. The model possesses analogies to biological neural structures and digital parallel port memories commonly used in parallel and multiprocessing systems.
Similar content being viewed by others
References
Bhatti AA (1987) State of the art research, development and applications of neural networks. D905-106065-1 High Technology Center, the Boeing Electronics Company, Bellevue, Washington
Bhatti AA (1990) Analysis of performance issues in neural network based associative memory models. IJCNN, San Diego, California, June
Bhatti AA (1992) Analysis of the effectiveness of using unipolar and bipolar binaries, and Hamming distance in neural network computing. J Opt Eng 31(9): 1972–1975
Bhatti AA, Ouyang YC (1990) Thresholding, hamming distance, unipolar/bipolar binaries, and retrieval in neural network based memories. IEEE 22nd SSST Conference Proceedings, Cookeville, Tennessee, March 11–13
Cottrel M (1988) Stability and attractivity in associative memory networks. Biol Cybern 58: 129–139
Daniele C, Costantini G, Perfetti R, Ricci E (2006) Associative memory design using support vector machines. IEEE Trans Neural Netw 17(5): 1165–1174
Farhat N (1986) Optoelectronics builds viable neural-net memory. Electronics, pp 41–44
Guan S-U, Chunyn B, TseNgee N (2007) Reduced pattern training based on task decomposition using pattern distributor. IEEE Trans Neural Netw 18(6): 1738–1749
Hirai Y (1982) A learning network resolving multiple match in associative memory. In: Proceedings of 6th international conference on pattern recognition
Hopfield JJ (1984) Neurons with graded response, have computational properties like those of two state neurons. Proc Natl Acad Sci 81: 3080
Hwang J-D, Hsiao F-H (2003) Stability analysis of neural-network interconnected systems. IEEE Trans Neural Netw 14(1): 201–208
Kosko B (1988) Bi-directional associative memories. IEEE Trans SMC 18: 49–60
Lee D-L, Chuang TC (2005) Designing asymmetric Hopfield-type associative memory with higher order Hamming stability. IEEE Trans Neural Netw 16(6): 1464–1476
Liang X, Chen R-C, Guo X (2008) Pruning support vector machines without altering performances. IEEE Trans Neural Netw 19(10): 1793–1803
McEliece RJ, Posner EC, Rodemich ER, Venkatesh SS (1987) The capacity of the hopfield associative memory. IEEE Trans Inform Theory 33(4): 461–482
Muller K-R, Mike S, Ratsch G, Tsuda K, Scholkopf B (2001) An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw 12(2): 181–201
Papoulis A, Pillai SU (2002) Probability, random variables and stochastic processes, 4th edn. McGraw Hill, New York
Simpson PK (1990) Higher-ordered and interconnected bidirectional associate memories. IEEE Trans SMS 20(3): 637–653
Suykens JAK (2008) Data visualization and dimensionality reduction using kernel maps with reference point. IEEE Trans Neural Netw 19(9): 1501–1517
Shen D, Cruz JB Jr (2005) Encoding strategy for maximum noise tolerance bidirectional associative memory. IEEE Trans Neural Netw 16(2): 293–300
Tank DW, Hopfield J (1986) Simple neural optimization network an A/D converter, signal decision circuit, and a linear programming circuit. IEEE Trans Circuits Syst 33(5): 533–541
Teddy SD, Quek C, Lai EM-K (2008) PSECMAC: a novel self-organizing multiresolution associative memory architecture. IEEE Trans Neural Netw 19(4): 689–712
Wang L (2000) Heteroassociatve of spatio-temporal sequences with the bidirectional associative memory. IEEE Trans Neural Netw 11(6): 1503–1505
Wang J-H, Krile TF, Walkup JF (1990) Determination of the Hopfield associative memory characteristics using a single parameter. Neural Netw 3(3): 319–331
Wang T, Xinhua Z, Xiaoliang X (1994) Designing bidirectional associative memories with optimal stability. IEEE Trans Syst Man Cybern 24(5): 778–790
Wang T, Xinhua Z, Xiaoliang X, Xipeng X (1993) A neuron-weighted learning algorithm and its hardware implementation in associative memories. IEEE Trans Comput 42(5): 636–640
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bhatti, A.A. Reduced order multiport parallel and multidirectional neural associative memories. Biol Cybern 100, 395–407 (2009). https://doi.org/10.1007/s00422-009-0310-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00422-009-0310-0