Share Email Print
cover

Proceedings Paper

Improved dynamic neural filtering technique by Widrow-recurrent learning algorithm
Author(s): Abdullah Bal
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Neural network based image processing algorithms present numerous advantages due to their supervised adjustable weight and bias coefficients. Among various neural network architectures, dynamic neural networks, Hopfield and Cellular neural networks have been found inherently suitable for filtering applications. These kind of neural networks present two important features; supervised learnable and optimization properties. Using these properties, dynamic neural filtering technique has been developed based on Hopfield neural networks. The filtering structure involves adjustable a filter mask and 2D convolution operation instead of weight matrix operations. To improve the supervised training properties, Widrow-recurrent learning algorithm has been proposed in this paper. Since the proposed learning algorithm requires less computation, consumption time in the training stage has been decreased considerably compared to previous reported supervised techniques for dynamic neural filtering.

Paper Details

Date Published: 28 March 2005
PDF: 7 pages
Proc. SPIE 5818, Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks III, (28 March 2005); doi: 10.1117/12.604038
Show Author Affiliations
Abdullah Bal, Univ. of South Alabama (United States)


Published in SPIE Proceedings Vol. 5818:
Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks III
Harold H. Szu, Editor(s)

© SPIE. Terms of Use
Back to Top