Training a neural network using differential input

Details Training a neural network using differential input Training a neural network using differential input

1997-10-14

2000-10-03

Hafiz, Tariq R.

Data processing: artificial intelligence

Neural network

Learning method

706 23, G06N 304, G06N 306

Patent

active

061286095

ABSTRACT:
A neural network is trained using a training neural network having the same topology as the original network but having a differential network output and accepting also differential network inputs. This new training method enables deeper neural networks to be successfully trained by avoiding a problem occuring in conventional training methods in which errors vanish as they are propagated in the reverse direction through deep networks. An acceleration in convergence rate is achieved by adjusting the error used in training to compensate for the linkage between multiple training data points.

REFERENCES:
patent: 5283855 (1994-02-01), Motomura et al.
patent: 5367612 (1994-11-01), Bozich et al.
patent: 5649066 (1997-07-01), Lacher et al.

Affiliated with

Also associated with

Rating

Training a neural network using differential input does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Training a neural network using differential input, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Training a neural network using differential input will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-204644