Automatic Generation of Initial Weights and Estimation of Hidden Units for Pattern Classification Using Neural Networks

Authors:
Affiliations:
Venue:
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 2 - Volume 2
Year:
1998

Citing 3
Cited 0

Skeletonization: a technique for trimming the fat from a network via relevance assessment

Advances in neural information processing systems 1
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
The interchangeability of learning rate and gain in backpropagation neural networks

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

This study high lights on the subject of weight initialization in back-propagation feed-forward networks. Training data is analyzed and the notion of critical points is introduced for determining the initial weights and the number of hidden units. The proposed method has been applied to artificial data and the publicly available cancer database. The experimental outcomes indicate that the proposed method reduces training time and results in better solution.