Neural network having an optimized transfer function for each ne

Details Neural network having an optimized transfer function for each ne Neural network having an optimized transfer function for each ne

1992-02-18

1994-01-18

Fleming, Michael R.

395 24, 395 27, G06F 1500

Patent

active

052805646

ABSTRACT:
The characteristic data for determining the characteristics of the transfer functions (for example, sigmoid functions) of the neurons of the hidden layer and the output layer (the gradients of the sigmoid functions) of a neural network are learned and corrected in a manner similar to the correction of weighting data and threshold values. Since at least one characteristic data which determines the characteristics of the transfer function of each neuron is learned, the transfer function characteristics can be different for different neurons in the network independently of the problem and/or the number of neurons, and be optimum. Accordingly, a learning with high precision can be performed in a short time.

REFERENCES:
patent: 4945494 (1990-07-01), Penz et al.
patent: 5043913 (1991-08-01), Furutani
patent: 5046020 (1991-09-01), Filkin
patent: 5113483 (1992-05-01), Keeler et al.
patent: 5119469 (1992-06-01), Alkon et al.
patent: 5134685 (1992-07-01), Rosenbluth
patent: 5167006 (1992-11-01), Furuta et al.
patent: 5187680 (1993-02-01), Engeler

Affiliated with

Also associated with

Rating

Neural network having an optimized transfer function for each ne does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural network having an optimized transfer function for each ne, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network having an optimized transfer function for each ne will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1141940