K. Abbo, K., H. Abrahim, H., A. Abrahim, F. (2017). A new learning rate based on Andrei method for training feed-forward artificial neural networks. , 22(2), 109-112.
Khalil K. Abbo; Hassan H. Abrahim; Firdos A. Abrahim. "A new learning rate based on Andrei method for training feed-forward artificial neural networks". , 22, 2, 2017, 109-112.
K. Abbo, K., H. Abrahim, H., A. Abrahim, F. (2017). 'A new learning rate based on Andrei method for training feed-forward artificial neural networks', , 22(2), pp. 109-112.
K. Abbo, K., H. Abrahim, H., A. Abrahim, F. A new learning rate based on Andrei method for training feed-forward artificial neural networks. , 2017; 22(2): 109-112.

A new learning rate based on Andrei method for training feed-forward artificial neural networks

Tikrit Journal of Pure Science
Article 1, Volume 22, Issue 2, 2017, Pages 109-112
Authors
Khalil K. Abbo; Hassan H. Abrahim; Firdos A. Abrahim
Abstract
In this paper we developed a new method for computing learning rate for Back-propagation algorithm to train a feed-forward neural networks. Our idea is based on the approximating the inverse Hessian matrix for the error function originally suggested by Andrie. Experimental results show that the proposed method considerably improve the convergence rate of the Back-propagation algorithm for the chosen test problem
Statistics
Article View: 68
PDF Download: 38


Journal Management System. Powered by iJournalPro.com