Title :
A learning algorithm for time-discrete cellular neural networks
Author :
Harrer, Hubert ; Nossek, Josef A. ; Zou, Fan
Author_Institution :
Inst. for Network Theory & Circuit Design, Tech. Univ. of Munich, Germany
Abstract :
A supervised learning algorithm for time-discrete cellular neural networks is introduced. The algorithm is based on the relaxation method and can be used for the determination of suitable template coefficients. This is done by postulating the subsequent output state of all cells. The relaxation method is able to train the network to a desired parameter insensitivity. Incorporating symmetry constraints leads to a fast convergence. If there exists a solution at all, the relaxation method always terminates after a finite number of iteration steps. The algorithm can also be applied to perceptrons or discrete Hopfield nets containing a comparator characteristic as nonlinearity
Keywords :
iterative methods; learning systems; neural nets; relaxation theory; comparator characteristic; discrete Hopfield nets; iteration steps; learning algorithm; parameter insensitivity; perceptrons; relaxation method; supervised learning; template coefficients; time-discrete cellular neural networks; Cellular neural networks; Circuit synthesis; Image processing; Iterative algorithms; Neural networks; Object detection; Pattern recognition; Relaxation methods; Supervised learning; Very large scale integration;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170484