On h∞ filtering in feedforward neural networks training and pruning

Authors:
He-Sheng Tang;Song-Tao Xue;Rong Chen
Affiliations:
Research Institute of Structural Engineering and Disaster Reduction, Tongji University, Shanghai, China;Department of Architecture, School of Science and Engineering, Kinki University, Higashi Osaka City, Japan;Research Institute of Structural Engineering and Disaster Reduction, Tongji University, Shanghai, China
Venue:
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Year:
2006

Citing 13
Cited 0

Training multilayer perceptrons with the extended Kalman algorithm

Advances in neural information processing systems 1
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Bayesian regularization and pruning using a Laplace prior

Neural Computation
Parameter identification for uncertain plants using H∞ methods

Automatica (Journal of IFAC)
A quantitative study of experimental evaluations of neural network learning algorithms: current research practice

Neural Networks
Fast second order learning algorithm for feedforward multilayer neural networks and its applications

Neural Networks
Indefinite-quadratic estimation and control: a unified approach to H2 and H∞ theories

Indefinite-quadratic estimation and control: a unified approach to H2 and H∞ theories
A pruning method for the recursive least squared algorithm

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Investigating the role of saliency analysis with a neural network rainfall-runoff model

Computers & Geosciences - Special issue on GeoComp 99- GeoComputation and the Geosciences
Second Order Derivatives for Network Pruning: Optimal Brain Surgeon

Advances in Neural Information Processing Systems 5, [NIPS Conference]
Artificial neural networks in wave predictions at the west coast of Portugal

Computers & Geosciences
On the Kalman filtering method in neural network training and pruning

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

An efficient training and pruning method based on H∞ filtering algorithm is proposed for Feedforward neural networks (FNNs). A FNNs’ weight importance measure linking up prediction error sensitivity obtained from H∞ filtering training and a weight salience based pruning technique are derived. The results of extensive experimentation indicate that the proposed method provides better pruning results during the training process of the network without losing its generalization capacity, also provides a robust global optimization training algorithm for given arbitrary network structures.