A Learning Method for Neural Networks Based on a Pseudoinverse Technique

Article type: Research Article

Authors: Pal, Chinmoy | Hagiwara, Ichiro | Kayaba, Naoki | Morishita, Shin

Affiliations: Nissan Motor Corporation Research Center, Natsushima-cho, Yokosuka 237, Japan | Yokohama National University, Dept. of Naval Architecture and Ocean Engineering, 156 Tokiwadai, Hodogaya-ku, Yokohama 240, Japan

Abstract: A theoretical formulation of a fast learning method based on a pseudoinverse technique is presented. The efficiency and robustness of the method are verified with the help of an Exclusive OR problem and a dynamic system identification of a linear single degree of freedom mass-spring problem. It is observed that, compared with the conventional backpropagation method, the proposed method has a better convergence rate and a higher degree of learning accuracy with a lower equivalent learning coefficient. It is also found that unlike the steepest descent method, the learning capability of which is dependent on the value of the learning coefficient ν, the proposed pseudoinverse based backpropagation algorithm is comparatively robust with respect to its equivalent variable learning coefficient. A combination of the pseudoinverse method and the steepest descent method is proposed for a faster, more accurate learning capability.

DOI: 10.3233/SAV-1996-3306

Journal: Shock and Vibration, vol. 3, no. 3, pp. 201-209, 1996