Template-Type: ReDIF-Paper 1.0
Series: Tinbergen Institute Discussion Papers
Creation-Date: 1997-12-03
Number: 97-123/4
Author-Name: Johan F. Kaashoek
Author-Name: Herman K. van Dijk
Author-Email: hkvandijk@few.eur.nl
Author-Workplace-Name: Erasmus University Rotterdam
Title: A Simple Strategy to prune Neural Networks with an Application to Economic Time Series
Abstract: A major problem in applying neural networks is specifying  the sizeof the network. Even for moderately sized networks the number ofparameters may become large compared to the number of data. In thispaper network performance is examined while reducing the size of thenetwork through the use of multiple correlation coefficients andgraphical analysis of network output per hidden layer cell andinput layer cell.
File-Url: https://papers.tinbergen.nl/97123.pdf
File-Format: application/pdf
File-Size: 244076 bytes
Handle: RePEc:tin:wpaper:19970123