Title :
Some recent results on computing with `neural nets´
Author :
Siegelmann, Hava T. ; Sontag, Eduardo D.
Author_Institution :
Rutgers Univ., New Brunswick, NJ, USA
Abstract :
Neural networks, understood here as systems consisting of linearly interconnected dynamical elements (integrators in continuous-time, or delay lines in discrete time) and scalar nonlinearities, provide an appealing model of analog computation. The authors describe some recent results on the approximation properties and the computational capabilities of such dynamical systems
Keywords :
analogue computers; delay lines; integrating circuits; neural nets; analog computation; approximation properties; computational capabilities; delay lines; integrators; linearly interconnected dynamical elements; scalar nonlinearities; Analog computers; Computational modeling; Computer networks; Computer science; Delay lines; Mathematical model; Mathematics; Neural networks; Neurons; Power system modeling;
Conference_Titel :
Decision and Control, 1992., Proceedings of the 31st IEEE Conference on
Conference_Location :
Tucson, AZ
Print_ISBN :
0-7803-0872-7
DOI :
10.1109/CDC.1992.371169
