Dynamic tunneling based regularization in feedforward neural networks

Citation

Singh, Y.P. and RoyChowdhury, Pinaki (2001) Dynamic tunneling based regularization in feedforward neural networks. Artificial Intelligence, 131 (1-2). pp. 55-71. ISSN 00043702

[img] Text
1926.pdf
Restricted to Repository staff only

Download (140kB)

Abstract

This paper presents a new regularization method based on dynamic tunneling for enhancing generalization capability of multilayered neural networks. The proposed method enables escape through undesired sub-optimal solutions on the composite error surface by means of dynamic tunneling. Undesired sub-optimal solutions may be increased or introduced from regularized objective function. Hence, the proposed method is capable of enhancing the regularization property without getting stuck at sub-optimal values in search space. The regularization property and escape from the sub-optimal values have been demonstrated through computer simulations on two examples. (C) 2001 Elsevier Science B.V. All rights reserved.

Item Type: Article
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 09 Sep 2011 03:15
Last Modified: 06 Feb 2014 04:22
URII: http://shdl.mmu.edu.my/id/eprint/2685

Downloads

Downloads per month over past year

View ItemEdit (login required)