Neural-network content-addressable memory

Details Neural-network content-addressable memory Neural-network content-addressable memory

1989-11-17

1993-10-12

Fleming, Michael R.

Static information storage and retrieval

Magnetic bubbles

Guide structure

395 23, 365 49, G06F 1546

Patent

active

052533280

ABSTRACT:
A neural network content-addressable error-correcting memory system is disclosed including a plurality of hidden and visible processing units interconnected via a linear interconnection matrix. The network is symmetric and all self-connections are not present. All connections between processing units are present, except those connecting hidden units to other hidden units. Each visible unit is connected to each other visible unit and to each hidden unit. A mean field theory learning and retrieval algorithm is also provided. Bit patterns or code words are stored in the network via the learning algorithm. The retrieval algorithm retrieves error-corrected bit patterns in response to noisy or error-containing input bit patterns.

REFERENCES:
patent: 4660166 (1987-04-01), Hopfield
patent: 4719591 (1988-01-01), Hopfield et al.
patent: 4897811 (1990-01-01), Scofield
patent: 4901271 (1990-02-01), Graf
Rumelhart et al., Parallel Distributed Processing vol. 1: Foundations, 1986, MIT Press, pp. 282-314.
Hopfield, J. J., "Neurons with graded response have collective computational properties like those of two-state neurons", Proc. Natl. Acad. Sci., vol. 81, pp. 3088-3092 (1984).
Van Den Bout et al., "Graph Partitioning Using Annealed Neural Networks", IEEE Trans. on Neural Networks, Jun. 1990, pp. 192-203.
Almeida, L. B., "A learning rule for asynchronous perceptrons with feedback in a combinatorial environment", IEEE First Intl. Conf. on Neural Networks, vol. II, Jun. 1987, pp. 609-618.
Hartman, E., "A high storage capacity neural network content-addressable memory", Network, 1991, 315-334.
Alspector et al., "Performance of a stochastic learning microchip", from Advances in Neural Information Processing Systems I, Morgan-Kaufmann, 1989, pp. 748-760.
Cortes et al., "A Network System for Image Segmentation", Intl. Conf. Neural Networks, 1989, pp. 121-125.
Bilbro et al., "Optimization by Mean Field Annealing", from Advances in Neural Information Processing Systems I, Morgan-Kaufmann, 1989, pp. 91-98.
Ogura et al., "A 20-Kbit Associative Memory LSI for Artificial Intelligence Machines", IEEE Jou. Solid-State Circuits, vol. 24(4), Aug. 1989, pp. 1014-1020.
Peterson and Hartman, "Explorations of Mean-Field Theory Learning Algorithm," MCC-ACA-ST/HI-065-88, Microelectronics and Computer Technology Corporation (1988).
Hopfield and Tank, "Computing with Neural Circuits: A Model," Science vol. 233, pp. 622-633 (1986).
Hopfield, "Neural Networks and Physical Systems with Emergent Collective Computational Abilities", Proceedings of the National Academy of Science, U.S.A., vol. 79, pp. 2554-2558 (1982).
Crick and Mitchison, "The Function of Dream Sleep," Nature, vol. 34, pp. 111-114 (1983).
Hopfield, Feinstein and Palmer, "Unlearning Has Stabilizing Effects in Collective Memories," Nature, vol. 304, pp. 158, 159 (1983).
Diedrich and Opper, "Learning of Correlated Patterns in Spin-Glass Networks by Local Learning Rules," Physical Review Letters, vol. 58, pp. 949-952 (1987).
E. Gardner, "Maximum Storage Capacity in Neural Networks," Europhysics Letters, 4 (4), pp. 481-485 (1987).
Krauth and Mezard, "Learning Algorithms with Optimal Stability in Neural Networks," Journal of Physics A; Math. Gen., vol. 20, pp. 1745-1752 (1987).
Wallace, "Memory and Learning in a Class of Neural Networks Models," Lattice Gauge Theory--A Challenge to Large Scale Computing, Bunk and Mutter, Editors, New York: Plenum (1986).
Venkatesh, "Epsilon Capacity of Neural Networks," in J. S. Denker (Ed.), Neural Networks for Computing, Snowbird, Utah, 1986, American Institute of Physics Conference Proceedings, p. 151 (1986).
Hopfield and Tank, "`Neural` Computation of Decisions in Optimization Problems," Biol. Cybern. 52, 141-152 (1985).
Peter and Anderson, "A Mean Field Theory Learning Algorithm for Neural Networks," Complex Systems 1, pp. 995-1019 (1987).

Affiliated with

Also associated with

Rating

Neural-network content-addressable memory does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural-network content-addressable memory, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural-network content-addressable memory will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1912282