Synthesis of threshold networks

Details Synthesis of threshold networks Synthesis of threshold networks

1996-09-05

1999-11-09

Gordon, Paul P.

Boots, shoes, and leggings

36414801, 706 25, G06F 1518, G05B 1302

Patent

active

059800798

ABSTRACT:
The learning algorithm called Expand-and-Truncate Learning (ETL) is invented to synthesize a three-layer threshold network (TLTN) with guaranteed convergence for an arbitrary switching function. There has not yet been found an algorithm to synthesize a threshold network for an arbitrary switching function. The most significant contribution of this invention is the development of a learning algorithm for a three-layer TLTN which guarantees convergence for any switching function, automatically determining a required number of threshold elements in the hidden layer. For example, it turns out that the required number of threshold elements in the hidden layer of a TLTN for an n-bit parity function is equal to n. The threshold element in the proposed TLTN employs only integer weights and integer thresholds. Therefore, this will greatly facilitate actual hardware implementation of the proposed TLTN using currently available digital VLSI technology.

REFERENCES:
patent: 5297237 (1994-03-01), Masuoka et al.
patent: 5353207 (1994-10-01), Keeler et al.
patent: 5396565 (1995-03-01), Asogawa
patent: 5555439 (1996-09-01), Higashino et al.

Affiliated with

Also associated with

Rating

Synthesis of threshold networks does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Synthesis of threshold networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Synthesis of threshold networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1446621