DocumentCode
2970952
Title
Application of neural networks to sorting problems
Author
Gray, D.L. ; Michel, A.N. ; Porod, W.
Author_Institution
Dept. of Electr. & Comput. Eng., Notre Dame Univ., IN, USA
fYear
1988
fDate
7-9 Dec 1988
Firstpage
350
Abstract
The authors present a design philosophy for constraint optimization problems which is based on viewing the neural network as an interconnection of several subsystems. Specifically, they present a method to classify ranges in the magnitude of an analog input signal and associate an arbitrary digital output with each range. The proposed approach is illustrated by application to a cascadable 2-bit analog/digital converter. The advantages of the proposed design method as compared with energy function designs are enumerated
Keywords
analogue-digital conversion; hybrid computers; neural nets; sorting; A/D converter; constraint optimization problems; design; neural networks; sorting problems; Analog-digital conversion; Application software; Constraint optimization; Integrated circuit interconnections; Intelligent networks; Matrix converters; Matrix decomposition; Neural networks; Neurons; Sorting;
fLanguage
English
Publisher
ieee
Conference_Titel
Decision and Control, 1988., Proceedings of the 27th IEEE Conference on
Conference_Location
Austin, TX
Type
conf
DOI
10.1109/CDC.1988.194327
Filename
194327
Link To Document