Single layer neural network circuit for performing linearly sepa

Details Single layer neural network circuit for performing linearly sepa Single layer neural network circuit for performing linearly sepa

1992-10-05

1994-10-11

MacDonald, Allen R.

395 27, G06F 1518

Patent

active

053554361

ABSTRACT:
A neural network provides both linearly separable and non-linearly separable logic operations, including the exclusive-or operation, on input signals in a single layer of circuits. The circuit weights the input signals with complex weights by multiplication and addition, and provides weighted signals to a neuron circuit (a neuron body or soma) which provides an output corresponding to the desired logical operation.

REFERENCES:
patent: 3735403 (1973-05-01), Sykes
patent: 4237737 (1980-12-01), Nitadori
patent: 4747150 (1988-05-01), Knutson et al.
patent: 4904881 (1990-02-01), Castro
patent: 4999525 (1991-03-01), Park et al.
patent: 5052043 (1991-09-01), Gaborski
patent: 5103431 (1992-04-01), Freeman et al.
patent: 5131072 (1992-07-01), Yoshizawa et al.
patent: 5161203 (1992-11-01), Buckley
Widrow, et al., "Learning Phenomena in Layered Neural Networks", IEEE First nter Conf. on Neural Networks Jun. 1987.
Widrow, et al., "The Complex LMS Algorithm", Proceedings of the IEEE Apr. 19, 1975 pp. 719-720.

Affiliated with

Also associated with

Rating

Single layer neural network circuit for performing linearly sepa does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Single layer neural network circuit for performing linearly sepa, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Single layer neural network circuit for performing linearly sepa will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1665047