Title :
A universal structure for artificial neural networks
Author :
Rauf, Fawad ; Ahned, H.M.
Author_Institution :
Dept. of Electr. & Comput. Sci., Boston Univ., MA, USA
Abstract :
An approximation procedure, named successive linearization, is introduced for unified implementation of a large class of neural networks. A nonlinear neural model with dynamic sensitivity is presented. It is modular and has rapid learning schemes. Arbitrary nonlinear functions with memory which are commonly used for modeling dynamical systems, as well as static nonlinear classification boundaries, can both be implemented equally well. Fast learning algorithms for the universal structure are presented
Keywords :
learning (artificial intelligence); neural nets; approximation procedure; artificial neural networks; dynamic sensitivity; nonlinear functions; rapid learning schemes; static nonlinear classification boundaries; successive linearization; Artificial neural networks; Associative memory; Geometry; Laboratories; Linear approximation; Multi-layer neural network; Neural networks; Neurons; Parameter estimation; Polynomials;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298538
