System for spatial and temporal pattern learning and recognition

Details System for spatial and temporal pattern learning and recognition System for spatial and temporal pattern learning and recognition

1991-08-13

1994-05-17

Fleming, Michael R.

G06F 1518, G06K 962

Patent

active

053135580

ABSTRACT:
A neural network simulator that comprises a sensory window memory capable of providing a system of neuron elements with an input consisting of data generated from sequentially sampled spatial and/or temporal patterns. Each neuron element comprises multiple levels, each of which is independently connected to the sensory window and/or to other neuron elements for receiving information corresponding to spatial and/or temporal patterns to be learned or recognized. Each neuron level comprises a multiplicity of pairs of synaptic connections that record ratios of input information so received and compare them to prerecorded ratios corresponding to learned patterns. The comparison is carried out for each synaptic pair according to empirical activation functions that produce maximum activation of a particular pair when the current ratio matches the learned ratio. When a sufficiently large number of synaptic pairs in a level registers a high activation, the corresponding neuron is taken to have recognized the learned pattern and produces a recognition signal.

REFERENCES:
patent: 4941122 (1990-07-01), Weideman
Hopfield, J. et al., "Computing with Neural Circuits: A Model", Science, vol. 233, Aug. 8, 1986, pp. 625-633.
Dehaene, S. et al., "Neural Networks that Learn Temporal Sequences by Selection", Proc. Natl. Acad. Sci. USA, vol. 84, May 1987, Biophysics, pp. 2727-2731.
Fukushima, K. "A Neural Network for Visual Pattern Recognition", Computer, Mar. 1988, pp. 65-75.
Carpenter, G. et al., "The Art of Adaptive Pattern Recognition by a Self-Organizing Neural Network", Computer, Mar. 1988, pp. 77-88.
Cric, F., "The Recent Excitement about Neural Networks", Nature, vol. 337, Jan. 12, 1989, pp. 129-132.
Lukashin, A., "A learned Neural Network that Simulates Properties of the Neuronal Population Vector", Biological Cybernetics, vol. 63, 1990, pp. 377-382.
Rumelhart et al., "Parallel Distributed Processing", vol. 1, MIT Press 1986.

Affiliated with

Also associated with

Rating

System for spatial and temporal pattern learning and recognition does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with System for spatial and temporal pattern learning and recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System for spatial and temporal pattern learning and recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-883832