State analog neural network and method of implementing same

Boots – shoes – and leggings

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

307201, 364513, G06G 712

Patent

active

049474820

ABSTRACT:
A neural network is implemented by discrete-time, continuous voltage state analog device in which neuron, synapse and synaptic strength signals are generated in highly parallel analog circuits in successive states from stored values of the interdependent signals calculated in a previous state. The neuron and synapse signals are refined in a relaxation loop while the synaptic strength signals are held constant. In learning modes, the synaptic strength signals are modified in successive states from stable values of the analog neuron signals. The analog signals are stored for as long as required in master/slaver sample and hold circuits as digitized signals which are periodically refreshed to maintain the stored voltage within a voltage window bracketing the original analog signal.

REFERENCES:
patent: 3950733 (1976-04-01), Cooper et al.
patent: 4573142 (1986-02-01), Azegami
patent: 4593370 (1986-06-01), Balkanli
"Self Organization of Orientation Sensitive Cells in the Striate Cortex", Chr. Von der Malsburg, Kybernetik 14, pp. 85-100, (1973).
"Development of Ocularity Domains and Growth Behaviour of Axon Terminals", C. Von der Malsburg, Biological Cybernetics 32, pp. 42-62 (1979).
"How Patterned Neural Connections Can be Set up by Self-Organization", D. J. Willshaw and C. Von der Malsburg, Proceedings of Royal Society of London Series B., vol. 194, pp. 431-445 (1976).
"Specificity and Plasticity of Retinotectal Connections: A Computational Model", V. A. Whitelaw and J. D. Cowan, The Journal of Neuroscience, vol. 1, No. 12, pp. 1369-1387, Dec. 1981.
"What Bell Laboratories is Learning from Slugs", John Paul Newport, Jr., Fortune, Apr. 1, 1985.
"Neutral Research Yields Computer that Can Learn", Chappell Brown, Electronic Engineering Times, Feb. 3, 1986.
Digital Integrated Electronic, Herbert Taub and Donald Schilling, pp. 420-428, McGraw-Hill, Inc. (1977).
Electronics for the Modern Scientist, Chapter 7: Digital Signal Processing, Paul B. Brown, Gunter N. Franz, Howard Moraff, pp. 410-426, Elsevie Science Publishing Co., Inc. (1982).

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

State analog neural network and method of implementing same does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with State analog neural network and method of implementing same, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and State analog neural network and method of implementing same will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-966571

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.