Journal Article

·2004

Wavelet-cellular neural network architecture and learning algorithm

Abdullah Bal YTU , Osman N. Uçan , Halit Pastaci YTU , Mohammad S. Alam

Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE

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.

Keywords

Cellular neural network Computer science Wavelet Algorithm Backpropagation Wavelet transform Artificial intelligence Function (biology) Artificial neural network Deep learning Activation function Image processing Image (mathematics) Pattern recognition (psychology)

Subject Areas

Neural Networks Stability and Synchronization ·Computer Networks and Communications ·Physical Sciences
Cellular Automata and Applications ·Computational Theory and Mathematics ·Physical Sciences
Quantum-Dot Cellular Automata ·Computational Theory and Mathematics ·Physical Sciences

Citations by Year