Simple Supervised Learning Algorithm for Recurrent Neural Network

Summary

A simple supervised learning algorithm for recurrent neural networks is proposed. It needs only O(n2) memories and O(n2) calculations where n is the number of neurons, by limiting the problems to delayed recognition (short-term memory) problem. Since O(n2) is the same as the order of the number of connections in the neural network, it is reasonable for implementation. This learning algorithm is similar to the conventional static back-propagation learning. Connection weights are modified by the products of the propagated error signal and some variables that hold the information about the past pre-synaptic neuron's output.

Reference

2. K. Shibata, Y. Okabe and K. Ito : (PSfile(gzip) 196kB A4 6 pages)

"Simple Learning Algorithm for Recurrent Networks to Realize Short-Term Memories",

Proc. of IJCNN'98, 1998

1. K. Shibata, Y. Okabe and K. Ito 柴田克成，岡部洋一，伊藤宏司 :

(PSfile(gzip) 78kB A4 2 pages in Japanese)

短期記憶のためのリカレントネット簡易学習則の基本構想

日本神経回路学会第8回全国大会論文予稿集, , 1997.11