Handwritten digit recognition using multi-layer feedforward neural networks with periodic and monotonic activation functions

Research output: Journal Publications and ReviewsRGC 22 - Publication in policy or professional journal

16 Scopus Citations
View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)106-109
Journal / PublicationProceedings - International Conference on Pattern Recognition
Volume16
Issue number3
Publication statusPublished - 2002

Abstract

The problem of handwritten digit recognition is tackled by multi-layer feedforward neural networks with different types of neuronal activation functions. Three types of activation functions are adopted in the network, namely, the traditional sigmoid function, the sinusoidal function and a periodic function that can be considered as a combination of the first two functions. To speed up the learning, as well as to reduce the network size, the Extended Kalman Filter (EKF) algorithm conjunct with a pruning method is used to train the network. Simulation results show that periodic activation functions perform better than monotonic ones in solving multi-cluster classification problems such as handwitten digit recognition. ©2002 IEEE.

Citation Format(s)

Handwritten digit recognition using multi-layer feedforward neural networks with periodic and monotonic activation functions. / Wong, Kwok-Wo; Leung, Chi-Sing; Chang, Sheng-Jiang.
In: Proceedings - International Conference on Pattern Recognition, Vol. 16, No. 3, 2002, p. 106-109.

Research output: Journal Publications and ReviewsRGC 22 - Publication in policy or professional journal