Title :
Singular perturbations and time scales in artificial neural networks
Author :
Moore, Kevin L. ; Naidu, D. Subbaram
Author_Institution :
Coll. of Eng., Idaho State Univ., Pocatello, ID, USA
Abstract :
The learning and computing processes in a recursive neural network of the Hopfield type are identified as slow and fast phenomena. The corresponding dynamical equations are cast to fit into the framework of the theory of singular perturbations and time scales. The issues of degeneration and asymptotic expansions arising in obtaining approximate solutions are addressed
Keywords :
Hopfield neural nets; learning (artificial intelligence); Hopfield neural nets; asymptotic expansions; dynamical equations; recursive neural network; singular perturbations; time scales; Artificial neural networks; Automatic control; Computer networks; Control systems; Differential equations; Equations; Hopfield neural networks; Intelligent networks; Manufacturing automation; Neural networks; Neurons; Nonlinear equations;
Conference_Titel :
Decision and Control, 1991., Proceedings of the 30th IEEE Conference on
Conference_Location :
Brighton
Print_ISBN :
0-7803-0450-0
DOI :
10.1109/CDC.1991.261077
