Generalization by Weight-Elimination with Application to Forecasting
作者： David E. Rumelhart , Andreas S. Weigend , Bernardo A. Huberman
DOI:
关键词:
摘要: Inspired by the information theoretic idea of minimum description length, we add a term to the back propagation cost function that penalizes network complexity. We give the details of …
nips.cc
acm.org 参考文章(5)
Jorma Rissanen, Stochastic Complexity In Statistical Inquiry ,(1989)
Andreas S. Weigend, David E. Rumelhart, Bernardo A. Huberman, BACK-PROPAGATION, WEIGHT-ELIMINATION AND TIME SERIES PREDICTION Connectionist Models. Proceedings of the 1990 Connectionist Models Summer School. pp. 105- 116 ,(1991) , 10.1016/B978-1-4832-1448-1.50016-0
Andreas Sebastian Weigend, Connectionist architectures for time series prediction of dynamical systems Ph.D. Thesis. ,(1991)
Andreas S. Weigend, Bernardo A. Huberman, David E. Rumelhart, PREDICTING THE FUTURE: A CONNECTIONIST APPROACH International Journal of Neural Systems. ,vol. 01, pp. 193- 209 ,(1990) , 10.1142/S0129065790000102
Howell Tong, Non-linear time series. A dynamical system approach Oxford Statistical Science Series. ,(1990)