Please use this identifier to cite or link to this item: http://hdl.handle.net/1783.1/52

Constructive feedforward neural networks for regression problems : a survey

Authors Kwok, Tin-Yau
Yeung, Dit-Yan
Issue Date 1995-09
Summary In this paper, we review the procedures for constructing feedforward neural networks in regression problems. While standard back-propagation performs gradient descent only in the weight space of a network with fixed topology, constructive procedures start with a small network and then grow additional hidden units and weights until a satisfactory solution is found. The constructive procedures are categorized according to the resultant network architecture and the learning algorithm for the network weights.
Language English
Format Technical report
Access
Files in this item:
File Description Size Format
tr9543.pdf 284422 B Adobe PDF