Title :
A learning algorithm for the dynamics of CNN with nonlinear templates. II. Continuous-time case
Author :
Puffer, E. ; Tetzlaff, R. ; Wolf, D.
Author_Institution :
Inst. fur Angewandte Phys., Frankfurt Univ., Germany
Abstract :
A gradient-based learning algorithm for the dynamics of continuous-time CNN with nonlinear templates is presented. It is applied in order to find the parameters of CNN that model the dynamics of certain multidimensional nonlinear systems, which are characterized by partial differential equations (PDE). The efficiency of the algorithm is compared to that of a non-gradient-based learning procedure we have previously developed. Results for modeling two systems, whose dynamics are determined by nonlinear Klein-Gordon-equations, are discussed in detail
Keywords :
cellular neural nets; continuous time systems; dynamics; learning (artificial intelligence); multidimensional systems; nonlinear systems; partial differential equations; continuous-time CNN; dynamics; efficiency; gradient-based learning algorithm; multidimensional nonlinear systems; nongradient-based learning procedure; nonlinear Klein-Gordon-equations; nonlinear templates; partial differential equations; Cellular neural networks; Computer aided software engineering; Context modeling; Convergence; Heuristic algorithms; Multidimensional systems; Nonlinear equations; Nonlinear systems; Partial differential equations; Steady-state;
Conference_Titel :
Cellular Neural Networks and their Applications, 1996. CNNA-96. Proceedings., 1996 Fourth IEEE International Workshop on
Conference_Location :
Seville
Print_ISBN :
0-7803-3261-X
DOI :
10.1109/CNNA.1996.566619
