Browse Prior Art Database

FAST RANDOM TRAINING METHOD FOR RECURRENT BACKPROPAGATION NEURAL NETWORKS

IP.com Disclosure Number: IPCOM000007108D
Original Publication Date: 1994-Feb-01
Included in the Prior Art Database: 2002-Feb-26

Publishing Venue

Motorola

Related People

Authors:
Orhan Karaali

Abstract

The following techniques make it possible to train recurrent backpropagation networks in. random mode. They also speed up the training of recurrent neural nets in a random mode by as much as a factor of two. Random mode training of recurrent nets is achieved by keeping all the past neural network out- put states in the recurrent buffer. Networks trained in random mode converge to lower error rates in comparison to sequential mode trained networks.