Continuation-based learning algorithm for discrete-time cellular neural networks

Autor:	G. Papoutsis, H. Magnussen, Josef A. Nossek
Rok vydání:	2002
Předmět:	Nonlinear system Discrete time and continuous time Computer science Cellular neural network Sigmoid function Differentiable function Dynamical system Algorithm Electronic mail Variable (mathematics)
Zdroj:	Proceedings of the Third IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94).
DOI:	10.1109/cnna.1994.381689
Popis:	The SGN-type nonlinearity of a standard discrete-time cellular neural network (DTCNN) is replaced by a smooth, sigmoidal nonlinearity with variable gain. Therefore, the resulting dynamical system is fully differentiable. Bounds on gain of the sigmoidal function are given, so that the new smooth system approximates the standard DTCNN within certain limits. A learning algorithm is proposed, which finds the template parameters for the standard DTCNN by gradually increasing the gain of the sigmoidal function. >
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::cdb399fc7e85882dcf60756c1e20c251 https://doi.org/10.1109/cnna.1994.381689 Zobrazit plný text záznamu