eCite Digital Repository

An Adaptive Activation Function for Higher Order Neural Networks


Xu, S and Zhang, M, An Adaptive Activation Function for Higher Order Neural Networks, Proceedings / AI 2002: Advances in Artificial Intelligence, 2-6 December 2002, Canberra, Australia, pp. 356-362. ISBN 3-540-00197-2 (2002) [Refereed Conference Paper]

DOI: doi:10.1007/3-540-36187-1_31


© Springer-Verlag Berlin Heidelberg 2002. This paper deals with higher order feed-forward neural networks with a new activation function - neuron-adaptive activation function. Experiments with function approximation and stock market movement simulation have been conducted to justify the new activation function. Experimental results have revealed that higher order feed-forward neural networks with the new neuron-adaptive activation function present several advantages over traditional neuron-fixed higher order feed-forward networks such as much reduced network size, faster learning, and more accurate financial data simulation.

Item Details

Item Type:Refereed Conference Paper
Research Division:Information and Computing Sciences
Research Group:Machine learning
Research Field:Neural networks
Objective Division:Information and Communication Services
Objective Group:Other information and communication services
Objective Field:Other information and communication services not elsewhere classified
UTAS Author:Xu, S (Dr Shuxiang Xu)
ID Code:25964
Year Published:2002
Deposited By:Computing
Deposited On:2002-08-01
Last Modified:2015-02-24

Repository Staff Only: item control page