Title :
RNS neural networks
Author :
Martinelli, G. ; Perfetti, R.
Author_Institution :
INFO-COM Dept., Roma Univ., Italy
Abstract :
A type of perceptron based on a residue number system (RNS) implementation is introduced. Due to the scaling involved in the RNS, it operates with a particular periodic nonlinearity which increases its capability of problem solving. Two examples which clearly show that the RNS perceptron has better performance than the classical perceptron are presented. In both the examples the RNS perceptron solves a problem which is out of the possibility of the corresponding nonRNS perceptron
Keywords :
digital arithmetic; neural nets; problem solving; RNS neural networks; perceptron; periodic nonlinearity; problem solving; residue number system; scaling; Arithmetic; Artificial neural networks; Multilayer perceptrons; Neural networks; Neurons; Nonhomogeneous media; Nonlinear equations; Shape;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.112630
