Share Email Print

Proceedings Paper

New pruning techniques for constructive neural networks with application to image compression
Author(s): Liying Ma; Khashayar Khorasani
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Image compression is an important research domain in image processing. Recently, several neural netowkr (NN) based schemes developed in this are. In particular, constructive feed-forward neural networks have been attempted by many researchers to this problem. The constructive NN-based schemes are promising given their lower training cost, satisfactory performance and automatic determination of proper network size. In this paper, we first consider a NN- based technique that uses a constructive one-hidden-layer FNN for image compression. In standard NN-based schemes when a new hidden unit is added to the net the whole net is retrained while in this scheme the input-side weights are first trained and then all the network output-side weights are adjusted, resulting in a considerably less computational efforts. Next, two pruning techniques are proposed to remove the unnecessary input-side weights during the network construction, without sacrificing the performance of the network, to yield a smaller and a more economical network. To confirm the effectiveness of the prosed techniques, we have applied them to both regression problems and image compression. It has been found that a significant number of weights can be pruned without degenerating the network performance.

Paper Details

Date Published: 4 August 2000
PDF: 11 pages
Proc. SPIE 4052, Signal Processing, Sensor Fusion, and Target Recognition IX, (4 August 2000); doi: 10.1117/12.395080
Show Author Affiliations
Liying Ma, Concordia Univ. (Canada)
Khashayar Khorasani, Concordia Univ. (Canada)

Published in SPIE Proceedings Vol. 4052:
Signal Processing, Sensor Fusion, and Target Recognition IX
Ivan Kadar, Editor(s)

© SPIE. Terms of Use
Back to Top