Title :
System identification using neural networks
Author :
Mhaskar, H.N. ; Hahm, Nahmwoo
Author_Institution :
Dept. of Math., California State Univ., Los Angeles, CA, USA
Abstract :
We examine the complexity of neural networks required to approximate an unknown system to a given degree of accuracy. We establish lower bounds on the number of neurons, as well as constructing networks to “almost” achieve this lower bound in the worst case analysis. Our constructions are simple, deterministic, and involve no optimization based training, such as backpropagation
Keywords :
computational complexity; identification; neural nets; complexity; lower bounds; unknown system; worst case analysis; Control systems; Electrical engineering; Function approximation; Linear systems; Mathematics; Neural networks; Neurons; Nonlinear control systems; Nonlinear systems; System identification;
Conference_Titel :
Neural Networks for Signal Processing [1996] VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop
Conference_Location :
Kyoto
Print_ISBN :
0-7803-3550-3
DOI :
10.1109/NNSP.1996.548338
