Title :
A large scale neural network with nonlinear synapses
Author_Institution :
Electron. Lab., Swiss Federal Inst. of Technol., Zurich, Switzerland
fDate :
27 Jun-2 Jul 1994
Abstract :
In this paper, we prove the usefulness of multi-layer perceptrons with nonlinear synapses for real-size applications such as handwritten character recognition. We describe some simulations of a large scale neural network with nonlinear synapses. The convergence speed is shown to be better than for the networks with linear multipliers. Some issues concerning the VLSI implementation are discussed
Keywords :
VLSI; character recognition; multilayer perceptrons; VLSI implementation; convergence speed; handwritten character recognition; large scale neural network; multilayer perceptrons; nonlinear synapses; real-size applications; CMOS technology; Character recognition; Laboratories; Large-scale systems; Multilayer perceptrons; Neural networks; Neurons; Physics; Very large scale integration; Wires;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374188
