Evaluation of an anti-regularization technique in neural networks
Yoshihiko Hamamoto, Yoshihiro Mitani, H. Ishihara, Toshinori Hase, S. Tomita · 1996
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.