A second-order learning algorithm for mu
โ
Yi-Jen Wang; Chin-Teng Lin
๐
Article
๐
1998
๐
Elsevier Science
๐
English
โ 392 KB
This article proposes a new second-order learning algorithm for training the multilayer perceptron (MLP) networks. The proposed algorithm is a revised Newton's method. A forward-backward propagation scheme is first proposed for network computation of the Hessian matrix, H, of the output error functi