Title :
Computational learning theory applied to discrete-time cellular neural networks
Author :
Utschick, Wolfgang ; Nossek, Josef A.
Author_Institution :
Inst. for Network Theory & Circuit Design, Tech. Univ. Munchen
Abstract :
The theory of probably approximately correct (PAC) learning is applied to discrete-time cellular neural networks (DTCNNS). The Vapnik-Chervonenkis dimension of DTCNN is determined. Considering two different operation modes of the network, an upper bound of the sample size for a reliable generalization of DTCNN architecture is given
Keywords :
cellular neural nets; computational linguistics; learning (artificial intelligence); Vapnik-Chervonenkis dimension; computational learning theory; discrete-time cellular neural networks; operation modes; probably approximately correct learning; upper bound; Cellular neural networks; Circuit synthesis; Computer networks; Extraterrestrial measurements; Neural networks; Nonhomogeneous media; Probability distribution; Testing; Training data; Upper bound;
Conference_Titel :
Cellular Neural Networks and their Applications, 1994. CNNA-94., Proceedings of the Third IEEE International Workshop on
Conference_Location :
Rome
Print_ISBN :
0-7803-2070-0
DOI :
10.1109/CNNA.1994.381691
