A Fast Neural Network Learning with Guaranteed Convergence to Zero System Error (Special Section on Information Theory and Its Applications)

概要

論文の詳細を見る
It is thought that we have generally succeeded in establishing learning algorithms for neural networks, such as the back-propagation algorithm. However two major issues remain to be solved. First, there are possibilities of being trapped at a local minimum in learning. Second, the convergence rate is too slow. Chang and Ghaffar proposed to add a new hidden node,whenever stopping at a local minimum, and restart to train the new net until the error converges to zero. Their method designs newly generated weights so that the new net after introducing a new hidden node has less error than that at the original local minimum. In this paper, we propose a new method that improves their convergence rate. Our proposed method is expected to give a lower system error and a larger error gradient magnitude than their method at a starting point of the new net, which leads to a faster convergence rate. Actually, it is shown through numerical examples that the proposed method gives a much better perfor-mance than the conventional Chang and Ghaffar's method.
社団法人電子情報通信学会の論文
1996-09-25