Artificial neural networks including Boolean-complete compartmen

Details Artificial neural networks including Boolean-complete compartmen Artificial neural networks including Boolean-complete compartmen

1997-09-11

2000-04-18

Hafiz, Tariq R.

Data processing: artificial intelligence

Neural network

706 26, G06N 300, G06N 306

Patent

active

060526793

ABSTRACT:
Artificial neural networks include a plurality of artificial neurons and a plurality of Boolean-complete compartments, a respective one of which couples a respective pair of artificial neurons. By providing Boolean-complete compartments, spurious complement memories can be avoided. A Boolean-complete compartment includes a collection of at least four Boolean functions that represent input vectors to the respective pair of artificial neurons. The collection of at least four Boolean functions are selected from sixteen possible Boolean functions that can represent input vectors to the respective pair of artificial neurons. A count for each of the at least four Boolean functions is also provided. The count represents a number of occurrences of each of the at least four Boolean functions in input vectors to the respective pair of artificial neurons. In order to read the artificial neural network, the network also includes a collection of transfer functions, a respective one of which is associated with a respective one the sixteen possible Boolean functions.

REFERENCES:
patent: 3950733 (1976-04-01), Cooper et al.
patent: 4044243 (1977-08-01), Cooper et al.
patent: 4254474 (1981-03-01), Cooper et al.
patent: 4326259 (1982-04-01), Cooper et al.
patent: 4660166 (1987-04-01), Hopfield
patent: 4760604 (1988-07-01), Cooper et al.
patent: 4897814 (1990-01-01), Clark
patent: 4943931 (1990-07-01), Allen
patent: 4972363 (1990-11-01), Nguyen et al.
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5113367 (1992-05-01), Marrian et al.
patent: 5148385 (1992-09-01), Frazier
patent: 5265224 (1993-11-01), Maruno
patent: 5357597 (1994-10-01), Aparicio, IV et al.
patent: 5517597 (1996-05-01), Aparicio, IV et al.
Klaus-Uwe Hoffgen and Hans Ulrich Simon, Robust Trainability of Single Neurons, 92 Proc. of the 5th Annual ACM Workshop on Computational Learning Theory 428-39, Jul. 1992.
Ivan Stojmenovic, Completeness Criteria in Many-Valued Set Logic under Compositions with Boolean Functions, 94 Proc. of the 24th International Symposium on Multiple-Valued Logic 177-83, May 1994.

Affiliated with

Also associated with

Rating

Artificial neural networks including Boolean-complete compartmen does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Artificial neural networks including Boolean-complete compartmen, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Artificial neural networks including Boolean-complete compartmen will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2344866