Abstract
Since Hopfield published his work on an associative memory model, a large number of works have studied the model from several angles and showed in particular its weaknesses, and presented ways to overcome them. Most of the proposed solutions seem to us however not biologically plausible. In this paper we present a simple statistical analysis of two networks similar to the Hopfield net, and show that the usage of positive feedback enhances the net recognizing capability without jeopardizing the stability. We also describe a layered parallel network composed of modules, each module being a modified Hopfield net. We finally present computer simulation results to support our analytical findings. The most important principles of this network are supported by data from the world of neurobiology.
Similar content being viewed by others
References
Braham R (1988) A parallel associative pattern recognizer. Neural networks [Suppl.]. Pergamon Press, Oxford: (to be published)
Carpenter GA, Grossberg S (1987) A massively parallel architecture for a self-organizing neural pattern recognition machine. Comp Vision Grap Image Process 37:54–115
Fukushima K (1988) A Neural network for visual pattern recognition. IEEE Comput 21:65–75
Grossberg S (1971) Pavlovian pattern learning by nonlinear neural networks. Proc Natl Acad Sci USA 68:828–831
Grossberg S (1976) On the development of feature detectors in the visual cortex with applications to learning and reaction-diffusion systems. Biol Cybern 21:145–159
Grossberg S (1983) Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans Syst Man Cybern SMC-13:815–826
Grossberg S (1988) Nonlinear neural networks: principles, mechanisms and architectures. Neural Networks 1:17–61
Harth E (1983) Order and chaos in neural systems: an approach to the dynamics of higher brain functions. IEEE Trans Syst Man Cybern SMC-13:782–789
Hebb DO (1949) The organization of behaviour. Wiley, New York
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 have collective computational properties like those of two-state neurons. Proc Natl Acad Sci USA 81:3088–3092
Kandel ER (1979) Small systems of neurons. Sci Am 241:66–76
Kohonen T (1988) An introduction to neural computing. Neural Networks 1:3–16
Lynch G (1986) Synapses, circuits, and the beginnings of memory. MIT Press, Cambridge, Mass
Nass MM, Cooper LN (1975) A theory for the development of feature detecting cells in visual cortex. Biol Cybern 19:1–18
Palmer LA, Jones JP, Mullikin WH (1985) Functional organization of simple receptive fields. In: Rose D, Dobson VG (eds) Models of the visual cortex. Wiley, New York, pp 273–280
Partridge D (1987) What's wrong with neural architectures. Compcon Spring '87, San Francisco, Calif, USA, pp 35–38
Sherman SM (1985) ParallelW-, X-, andY-cell pathways in the cat: a model for visual function. In: Rose D, Dobson VG (eds) Models of the visual cortex. Wiley, New York, pp 71–82
Singer W (1985) Activity-dependent self-organization of the mammalian visual cortex. In: Rose D, Dobson VG (eds) Models of the visual cortex. Wiley, New York, pp 123–136
Stevens CF (1979) The Neuron. Sci Am 241:54–65
Stone J (1983) Parallel processing in the visual system. Plenum Press, New York
Van Der Loos H (1976) Neuronal circuitry and its developments. In: Progr Brain Res 45:259–278
Wallace DJ (1986) Memory and learning in a class of neural network models. In: Bunk B, Mutter KH, Schilling K (eds) In Lattice gauge theory, a challenge in large-scale computing. Plenum Press, New York, pp 313–330
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Braham, R., Hamblen, J.O. On the behavior of some associative neural networks. Biol. Cybern. 60, 145–151 (1988). https://doi.org/10.1007/BF00202902
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00202902