Feedforward networks training speed enhancement by optimal initialization of the synaptic coefficients

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)22_Publication in policy or professional journal

76 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)430-434
Journal / PublicationIEEE Transactions on Neural Networks
Volume12
Issue number2
Publication statusPublished - Mar 2001

Abstract

This letter aims at determining the optimal bias and magnitude of initial weight vectors based on multidimensional geometry. This method ensures the outputs of neurons are in the active region and the range of the activation function is fully utilized. In this letter, very thorough simulations and comparative study were performed to validate the performance of the proposed method. The obtained results on five well-known benchmark problems demonstrate that the proposed method deliver consistent good results compared with other weight initialization methods.