File(s) not publicly available
An Adaptive Activation Function for Higher Order Neural Networks
© 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.
History
Publication title
Proceedings / AI 2002: Advances in Artificial IntelligenceEditors
JG Carbonell & Jorg SiekmannPagination
356-362ISBN
3-540-00197-2Department/School
School of Information and Communication TechnologyPublisher
Springer -VerlagPlace of publication
GermanyEvent title
15th Australian Joint Conference on Artificial Intelligence Canberra, AustraliaEvent Venue
Canberra, AustraliaDate of Event (Start Date)
2002-12-02Date of Event (End Date)
2002-12-06Repository Status
- Restricted