Unipolar terminal-attractor based neural associative memory with

Details Unipolar terminal-attractor based neural associative memory with Unipolar terminal-attractor based neural associative memory with

1993-06-07

1996-08-06

Davis, George B.

395 21, 395 23, 395 11, 395 25, G06F 1546

Patent

active

055442803

ABSTRACT:
A unipolar terminal-attractor based neural associative memory (TABAM) system with adaptive threshold for perfect convergence is presented. By adaptively setting the threshold values for the dynamic iteration for the unipolar binary neuron states with terminal-attractors for the purpose of reducing the spurious states in a Hopfield neural network for associative memory and using the inner-product approach, perfect convergence and correct retrieval is achieved. Simulation is completed with a small number of stored states (M) and a small number of neurons (N) but a large M/N ratio. An experiment with optical exclusive-OR logic operation using LCTV SLMs shows the feasibility of optoelectronic implementation of the models. A complete inner-product TABAM is implemented using a PC for calculation of adaptive threshold values to achieve a unipolar TABAM (UIT) in the case where there is no crosstalk, and a crosstalk model (CRIT) in the case where crosstalk corrupts the desired state.

REFERENCES:
patent: 4660166 (1987-04-01), Hopfield
patent: 5014219 (1991-05-01), White
J. J. Hopfield, "Neural Networks and Physical Systems with Emergent Collective Computational Abilities," Proc. Nat. Acad. Sci., USA, vol. 79, pp. 2254-2258, Apr. 1982.
R. J. McEliece, et al., "The Capacity of the Hopfield Associative Memory," IEEE Transactions on Information Theory, vol. T-33, pp. 461-482, 1987.
B. L. Montgomery et al., "Evaluation of the use of Hopfield Neural Network Model as a Nearest Neighbor-Neighbor Algorithm," Appl. Optics, vol. 25, No. 20, pp. 3759-3766, 1986.
M. Zak, "Terminal Attractors for Addressable Memory in Neural Networks," Phys. Lett. vol. A-133, pp. 18-22, Oct., 1988.
M. Zak, "Terminal Attractors in Neural Networks," Neural Networks, vol. 2, pp. 259-274, 1989.
H. K. Liu, et al., "Optical Implementation of Terminal Attractor Based Associative Memory," Appl. Opt., vol. 31, pp. 4631-4644, Aug. 10, 1992.
S. Y. Kung, et al., "An Optical Inner-Product Array Processor for Associative Retrieval," Proc. SPIE, vol. 613, pp. 214-219, 1986.
H. K. Liu et al., "Liquid Crystal Television Spatial Light Modulators," Appl. Opt., vol. 28, pp. 4772-4780, 1989.
J. S. Bayley et al., "On the use of the Hopfield model for optical pattern recognition," Opt. Commun., vol. 64, pp. 105-110, 1987.
G. R. Gindi et al., "Hopfield model associative memory with nonzero-diagonal terms in memory matrix," Appl. Opt., vol. 27, pp. 129-134, 1988.
H. K. Liu et al., "Inner-product optical neural processing and supervised learning," First Annual Conference of the International Neural Network Society, (INNS), Boston, Mass., Sep. 6-10, 1988.
F. J. Pineda, "Generalization of Back-Propagation to Recurrent Neural Networks," Physical Review Letters, The American Physical Society, vol. 59, No. 19, pp. 2229-2232, 1987.
N. H. Farhat, "Optoelectronic analogs of self-programming neural nets: architecture and methodologies for implementing fast stochastic learning by simulated annealing," App. Opts., vol. 26, No. 23, pp. 5093-5103, 1987.
Taiwei Lu, et al., "Optical Implementation of Programmable Neural Networks, Optical Pattern Recognition", H. Liu, ed., Proc. Soc. Photo-Opt. Instrum. Eng., vol. 1053, pp. 30-39, 1989.
D. Psaltis et al., "Optical information processing based on an associative-memory model of neural nets with thresholding and feedbck," Optics Letters, vol. 10, No. 2, pp. 98-100, 1985.

Affiliated with

Also associated with

Rating

Unipolar terminal-attractor based neural associative memory with does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Unipolar terminal-attractor based neural associative memory with, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Unipolar terminal-attractor based neural associative memory with will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2198659