Title :
Tensor product neural networks and approximation of dynamical systems
Author :
Dingankar, Ajit T. ; Sandberg, Irwin W.
Author_Institution :
IBM Corp., Austin, TX, USA
Abstract :
We consider the problem of approximating any member of a large class of input-output operators of nonlinear dynamical systems. The systems need not be shift invariant, and the system inputs need not be continuous. We introduce a family of “tensor product” dynamical neural networks, and show that a certain continuity condition is necessary and sufficient for the existence of arbitrarily good approximations using this family
Keywords :
approximation theory; neural nets; nonlinear dynamical systems; tensors; approximation; continuity condition; input-output operators; nonlinear dynamical system; tensor product neural network; Extraterrestrial measurements; Integral equations; Neural networks; Nonlinear dynamical systems; Tensile stress;
Conference_Titel :
Circuits and Systems, 1996. ISCAS '96., Connecting the World., 1996 IEEE International Symposium on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3073-0
DOI :
10.1109/ISCAS.1996.541606
