Title :
Efficient implementation of neural nets using an optimal relationship between number of patterns, input dimension and hidden nodes
Author :
Mirchandani, Gagan ; Cao, Wei ; Bosworth, Barry
Author_Institution :
Dept. of Comput. Sci. & Electr. Eng., Vermont Univ., Burlington, VT, USA
Abstract :
Some key issues in the design of neural nets for pattern classification are topology and associated training samples required to obtain adequate performance with test samples. Currently, there does not exist an analytical framework within which to formulate the design of multilayer perceptrons. A theorem that relates input dimension, number of hidden nodes, and number of separable regions is given. The results of application to some experiments reported in the literature and to new experiments are analyzed
Keywords :
neural nets; pattern recognition; hidden nodes; input dimension; multilayer perceptrons; neural nets; optimal relationship; pattern classification; performance; separable regions; theorem; topology; training samples; Computer science; Identity-based encryption; Multi-layer neural network; Multilayer perceptrons; Network topology; Neural networks; Pattern classification; Sonar; Supervised learning; Testing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266980
