Share Email Print
cover

Proceedings Paper

Wavelet-cellular neural network architecture and learning algorithm
Author(s): Abdullah Bal; Osman Nuri Ucan; Halit Pastaci; Mohammad S. Alam
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Cellular Neural Networks (CNN) provides fast parallel computational capability for image processing applications. The behavior of the CNN is defined by two template matrices. In this paper, adjustment of these template-matrix coefficients have been realized using supervised learning algorithm based on back-propagation technique and wavelet function. Back-propagation algorithm has been modified for dynamic behavior of CNN. Wavelet function is utilized to provide the activation function derivation in this learning algorithm. The supervised learning algorithm is then executed to obtain a compact CNN architecture, called as Wave-CNN. The proposed new learning algorithm and Wave-CNN architecture performance have been tested for 2D image processing applications.

Paper Details

Date Published: 12 April 2004
PDF: 5 pages
Proc. SPIE 5439, Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks II, (12 April 2004); doi: 10.1117/12.542353
Show Author Affiliations
Abdullah Bal, Univ. of South Alabama (United States)
Osman Nuri Ucan, Istanbul Univ. (Turkey)
Halit Pastaci, Yildiz Technical Univ. (Turkey)
Mohammad S. Alam, Univ. of South Alabama (United States)


Published in SPIE Proceedings Vol. 5439:
Independent Component Analyses, Wavelets, Unsupervised Smart Sensors, and Neural Networks II
Harold H. Szu; Mladen V. Wickerhauser; Barak A. Pearlmutter; Wim Sweldens, Editor(s)

© SPIE. Terms of Use
Back to Top