Title :
Evaluation of an anti-regularization technique in neural networks
Author :
Hamamoto, Y. ; Mitani, Y. ; Ishihara, H. ; Hase, T. ; Tomita, S.
Author_Institution :
Fac. of Eng., Yamaguchi Univ., Ube, Japan
Abstract :
An anti-regularization technique which has been recently proposed by Raudys (1995) is studied in small training sample size situations. Experimental results show that as long as the weights of a network are initialized in a very narrow interval, the anti-regularization technique offers significant advantages in terms of both the generalization ability and learning time
Keywords :
generalisation (artificial intelligence); learning (artificial intelligence); pattern classification; perceptrons; anti-regularization; generalization; learning time; network weights; neural networks; pattern classifier; single layer perceptrons; Artificial neural networks; Cost function; Degradation; Intelligent networks; Neural networks;
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-8186-7282-X
DOI :
10.1109/ICPR.1996.547416
