Learning method for multi-level neural network

Details Learning method for multi-level neural network Learning method for multi-level neural network

1997-09-04

1998-06-09

Hafiz, Tariq R.

395 21, 395 24, G06E 100, G06F 1518

Patent

active

057648603

ABSTRACT:
A learning method supervised by a binary teacher signal for a binary neural network comprises at least an error signal generator 10 for weighting factor updating, which generates an error signal for weighting factor updating having an opposite polarity to that of a difference signal between an output unit signal of the binary neural network and the binary teacher signal on an output unit whereat a binary output unit signal coincides with the binary teacher signal, and an amplitude which decreases by increase of distance from the binary teacher signal, when an absolute value of the difference signal is smaller than a threshold, generates an error signal which has the same polarity as that of the difference signal and an amplitude smaller than that of the difference signal, when the absolute value of the difference signal is larger than the threshold, or generates an error signal which has an amplitude equal to or smaller than that of the difference signal on an output unit providing a wrong binary output unit signal which is different from the binary teacher signal. Updating the weighting factors by the error signal which is optimally generated according to discrimination between the correct binary output unit signal and the wrong one, can provide a binary neural network which converges very quickly and reliably to obtain a desired binary output and also realizes a high generalization ability.

REFERENCES:
patent: 5095443 (1992-03-01), Watanabe
patent: 5479538 (1995-12-01), Takahashi
patent: 5481293 (1996-01-01), Kanno
Mori et al. "A Recurrent Neural Network for Short Term Load Forecasting," ANNPS '93. Proc. of the 2nd Intern. Forum on Appl. of Neural Network to Power Systems, p. 395-400, Jan. 31, 1993.

Affiliated with

Also associated with

Rating

Learning method for multi-level neural network does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Learning method for multi-level neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning method for multi-level neural network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2211757