Title :
Analog neural systems
Author :
Dickinson, Bradley W.
Author_Institution :
Dept. of Electr. Eng., Princeton Univ., NJ, USA
Abstract :
Summary form only given. The author describes work in understanding the limitations of analog computing systems and their relevance to several problems involving neural networks. Two main themes are considered, both involving computational complexity considerations. The first theme involves the proposal that neural networks be used to solve the `intractable´ (NP-complete) combinatorial optimization problem. The second theme involves adaptation or learning algorithms for neural networks
Keywords :
analogue computers; computational complexity; neural nets; analogue computer systems; combinatorial optimization problem; computational complexity; learning algorithms; neural networks; Analog computers; Chaos; Computational complexity; Computational modeling; Computer networks; Neural networks; Predictive models; Turing machines;
Conference_Titel :
Decision and Control, 1988., Proceedings of the 27th IEEE Conference on
Conference_Location :
Austin, TX
DOI :
10.1109/CDC.1988.194419
