Abstract
The Hopfield model of neural network stores memory in its symmetric synaptic connections and can only learn to recognize sets of nearly “orthogonal” patterns. A new algorithm is put forth to permit the recognition of general (“non-orthogonal”) patterns. The algorithm specifies the construction of the new network's memory matrix T ij, which is, in general, asymmetrical and contains the Hopfield neural network (Hopfield 1982) as a special case. We find further that in addition to this new algorithm for general pattern recognition, there exists in fact a large class of T ij memory matrices which permit the recognition of non-orthogonal patterns. The general form of this class of T ij memory matrix is presented, and the projection matrix neural network (Personnaz et al. 1985) is found as a special case of this general form. This general form of memory matrix extends the library of memory matrices which allow a neural network to recognize non-orthogonal patterns. A neural network which followed this general form of memory matrix was modeled on a computer and successfully recognized a set of non-orthogonal patterns. The new network also showed a tolerance for altered and incomplete data. Through this new method, general patterns may be taught to the neural network.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Amado I (1987) Growing “brains” in a computer. Sci News 131:60–61
Anderson JA (1983) Cognitive and psychological computation with neuronal models. IEEE Trans SMC 13:799–815
Ballard DH (1986) Cortical connections and parallel processing: structure and function. Behav Brain Sci 9:67–120
Brown CM (1984) Computer vision and natural constraints. Science 224:1299–1305
Crick F, Mitchison G (1983) The function of dream sleep. Nature 304:111–114
Gelperin A, Hopfield JJ, Tank DW (1985) The logic of Limax learing. In: Selverston A (ed) Model neural networks and behavior. Plenum Press, New York
Grant PM, Sage JP (1986) A comparison of neural network and matched filter processing for detecting lines in images. In: 1986 Neural Networks for Computing Conf, Snowbird, UT, USA. AIP Conference Proc 151
Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA 79:2554–2558
Hopfield JJ (1984) Neurons with graded response that have collective computational properties like those of two-state neurons. Proc Natl Acad Sci USA 81:3088–3092
Hopfield JJ, Tank DW (1985) “Neural” computation of decisions in optimization problems. Biol Cybern 52:141–152
Hopfield JJ, Feinstein DI, Palmer RG (1983) “Unlearning” has a stabilizing effect in collective memories. Nature 304:158–159
Kinzel W (1985) Learning and pattern recognition in spin glass models. Z Phys B — Condensed Matter 60:205–213
Personnaz L, Guyon I, Drefus G (1985) Information storage and retrieval in spin-glass like neural networks. J Phys (Paris) Lett 46:L359-L365
Psaltis D, Farhat N (1986) Optical information processing based on an associative-memory model of neural nets with thresholding and feedback. Opt Lett 10:98–100
Shiozaki A (1980) A model of distributed type associative memory with quantized Hadamard transform. Biol Cybern 38:19–22
Tank DW, Hopfield JJ (1986) Simple “neural” optimization networks: an A/D converter, signal decision circuit, and a linear programming circuit. IEEE Trans CAS-33:533–541
Tesauro G (1986) Simple neural models of classical conditioning. Biol Cybern 55:187–200
von Neumann J (1966) Theory of self-reproducing automata. University of Illinois Press, Urbana London
Winston PH (1984) Artificial intelligence. Addison-Wesley, Reading, Mass
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wong, A.JW. Recognition of general patterns using neural networks. Biol. Cybern. 58, 361–372 (1988). https://doi.org/10.1007/BF00361344
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF00361344