Title :
Layered neural networks with horizontal connections can reduce the number of units
Author_Institution :
Dept. of Math., Morgan State Univ., Baltimore, MD, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
We define layered networks with horizontal connections as networks having units that receive inputs from the lower layer and also from the previous units of the same layer. We show that architecture with horizontal connections does not require as many units in the hidden layers as the plain layered architecture in order to approximate a function
Keywords :
approximation theory; function approximation; multilayer perceptrons; neural net architecture; parallel architectures; piecewise constant techniques; continuous function approximation; horizontal connections; layered neural networks; multilayer perceptron; piecewise constant function; Backpropagation algorithms; Computer architecture; Computer networks; Data systems; Mathematics; Neural networks; Nonhomogeneous media; Pursuit algorithms; Spirals; Strips;
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.1994.374480
