Improving Bayesian Regularization of ANN via Pre-training with Early-Stopping

Authors:
Z. S. H. Chan;H. W. Ngan;A. B. Rad
Affiliations:
Department of Electrical Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong;Department of Electrical Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong;Department of Electrical Engineering, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong. e-mail: eeabrad@polyu.edu.hk
Venue:
Neural Processing Letters
Year:
2003

Citing 4
Cited 1

Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Controling the Hyperparameter Search in MacKay's Bayesian Neural Network Framework

Neural Networks: Tricks of the Trade, this book is an outgrowth of a 1996 NIPS workshop
Pricing and hedging derivative securities with neural networks: Bayesian regularization, early stopping, and bagging

IEEE Transactions on Neural Networks
Minimizing risk using prediction uncertainty in neural network estimation fusion and its application to papermaking

IEEE Transactions on Neural Networks

Statistical and incremental methods for neural models selection

International Journal of Artificial Intelligence and Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a simple method that enhances the performance of Bayesian Regularization of Artificial Neural Network (ANN) through pre-training of initial network with the Early-Stopping algorithm. The proposed method is applied to the regularization of Feed-forward Neural Networks to regress three benchmark data series. Significant reduction in both the cross-validation error and the number of training over standard Bayesian Regularisation is achieved.