Highly parallel computation network employing a binary-valued T

Details Highly parallel computation network employing a binary-valued T Highly parallel computation network employing a binary-valued T

1986-04-14

1988-04-12

Smith, Jerry

Boots, shoes, and leggings

364133, G06G 702, G06G 700, G06F 1546

Patent

active

047379294

ABSTRACT:
Advantageous neural network realizations are achieved by employing only negative gain amplifiers and a clipped T matrix having conductances T.sub.ij which have only two values. Preferably, one of these values is a preselected value set by the value of a fixed resistor, and the other value is zero, created simply with an open circuit. Values for the T.sub.ij terms of the clipped T matrix are obtained through an iterative process which operates on the clipped and nonclipped matrices and minimizes the error resulting from the use of the clipped T matrix.

REFERENCES:
patent: 4218768 (1980-08-01), Hassler
patent: 4536844 (1985-08-01), Lyon
patent: 4660166 (1987-04-01), Hopfield
"Linear Programming on an Electronic Analogue Computer", Trans. AIEE Part I (Comm.&Elect.), vol. 75, I. B. Pyne, 1956, pp. 139-143.

Affiliated with

Also associated with

Rating

Highly parallel computation network employing a binary-valued T does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Highly parallel computation network employing a binary-valued T , we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Highly parallel computation network employing a binary-valued T will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1433885