Adaptive training and pruning in feedforward networks

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

3 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)106-107
Journal / PublicationElectronics Letters
Volume37
Issue number2
Publication statusPublished - 18 Jan 2001

Abstract

A local extended Kalman filter training and pruning approach is proposed to train feedforward networks. This approach is proposed specifically to reduce the computational complexity and storage requirement in large-scale practical problems. The performance of the proposed algorithm is demonstrated for the problem of handwritten digit recognition.

Citation Format(s)

Adaptive training and pruning in feedforward networks. / Chang, Sheng-Jiang; Sum, John; Wong, Kwok-Wo; Leung, Chi-Sing.

In: Electronics Letters, Vol. 37, No. 2, 18.01.2001, p. 106-107.

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