Neuron for use in self-learning neural network

Details Neuron for use in self-learning neural network Neuron for use in self-learning neural network

1994-01-06

1995-05-02

Westin, Edward P.

Electronic digital logic circuitry

Multifunctional or programmable

Array

395 21, 395 23, 326 36, H03K 1908, H03K 192

Patent

active

054122562

ABSTRACT:
A neuron for use in a self-learning neural network comprises a current input node at which a plurality of synaptic input currents are summed using Kirchoff's current law. The summed input currents are normalized using a coarse gain current normalizer. The normalized summed inputs current is then converted to a voltage using a current to voltage converter. This voltage is then amplified by a gain controlled cascode output amplifier. Gain control inputs are provided in the output amplifier so that the neuron can be settled by the Mean Field Approximation. A noise input stage is also connected to the output amplifier so that the neuron can be settled using simulated annealing. The resulting neuron is a variable gain, bi-directional current transimpedance neuron with a controllable noise input.

REFERENCES:
patent: 4874963 (1989-10-01), Alspector
patent: 5087826 (1992-02-01), Holler et al.
patent: 5107149 (1992-04-01), Platt et al.
patent: 5126685 (1992-06-01), Platt et al.
patent: 5165054 (1992-11-01), Platt et al.
patent: 5253329 (1993-10-01), Villarreal et al.
patent: 5336937 (1994-08-01), Sridhar et al.
J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities," Proceedings of the National Academy of Sciences, 1982, vol. 79, pp. 2554-2558.
D. H. Ackley et al., "A Learning Algorithm for Boltzmann Machines," Cognitive Science, 1985, vol. 9, pp. 147-169.
C. Peterson et al., "A Mean Field Theory Learning Algorithm for Neural Networks," Complex Systems, 1987, vol. 1, pp. 995-1019.
G. E. Hinton, "Deterministic Boltzmann Learning Performs Steepest Descent in Weight-Space," Neural Computation, 1989, vol. 1, pp. 143-150.
J. Alspector et al., "Performance of a Stochastic Learning Microchip," Proceedings of Advances in Neural Information Processing Systems, 1988, pp. 748-760.
J. Alspector et al., "Relaxation Networks for Large Supervised Learning Problems," Proceedings of Advances in Neural Information Processing Systems, 1991, pp. 1015-1021.
J. Alspector et al., "A VLSI-Efficient Technique for Generating Multiple Uncorrelated Noise Sources and Its Application to Stochastic Neural Networks," IEEE Transactions on Circuits and Systems, 1991, vol. 38, pp. 109-123.

Affiliated with

Also associated with

Rating

Neuron for use in self-learning neural network does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neuron for use in self-learning neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neuron for use in self-learning neural network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1139635