A New Approach to the Structural Learning of Neural Networks

Rameswar DEBNATH  Haruhisa TAKAHASHI  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E87-A   No.6   pp.1655-1658
Publication Date: 2004/06/01
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Neural Networks and Bioengineering
backpropagation,  structural learning,  Lagrangian differential gradient,  

Full Text: PDF>>
Buy this Article

Structural learning algorithms are obtained by adding a penalty criterion (usually comes from the network structure) to the conventional criterion of the sum of squared errors and applying the backpropagation (BP) algorithm. This problem can be viewed as a constrained minimization problem. In this paper, we apply the Lagrangian differential gradient method to the structural learning based on the backpropagation-like algorithm. Computational experiments for both artificial and real data show that the improvement of generalization performance and the network optimization are obtained applying the proposed method.