H filtering method for neural network training and pruning

Title:

H filtering method for neural network training and pruning

Creator:

Tang, He-Sheng, Xue, Song-Tao, Chen, Rong, and Sato, Tadanobu

Identifier:

https://cdk.lib.cas.cz/client/handle/uuid:adb7d30e-9cdf-45bf-9908-5664a71b7a98
uuid:adb7d30e-9cdf-45bf-9908-5664a71b7a98

Subject:

H filtering, feedforward neural network, training, and pruning

Type:

model:article and TEXT

Format:

bez média and svazek

Description:

An efficient training and pruning method based on the HY filtering algorithm is proposed for feedforward neural networks (FNN). A FNN's weight importance measure linking up prediction error sensitivity obtained from the HY filtering training, and then a weight salience based pruning algorithm is derived. Moreover, based on the monotonicity property of the HY filtering Riccati equation and the initial value of the error covariance matrix, performance of the HY filtering training algorithm will also be investigated. The simulation results show that our approach is an effective training and pruning method for neural networks.

Language:

English

Rights:

http://creativecommons.org/publicdomain/mark/1.0/
policy:public

Source:

Neural network world: international journal on neural and mass-parallel computing and information systems | 2007 Volume:17 | Number:1

Harvested from:

CDK

Metadata only:

false