Conference paper
Learning functions and their derivatives using Taylor series and neural networks
IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339), Vol.1, pp.409-412
IEEE
International Joint Conference on Neural Networks, IJCNN 99 (Washington, DC, USA, 10/07/1999–16/07/1999)
1999
Abstract
This paper describes a design based on the Taylor series to approximate a function and its derivatives. After being trained, derivatives are obtained in a fast feedforward evaluation without the need for back propagation or forward perturbation. The Taylor network is basically an implementation of the Taylor series of a function. However, instead of only having one expansion point, it uses a function of expansion points and takes account of the order of the Taylor series by biasing individual terms of the Taylor series. A simple learning algorithm is given and demonstrated with a simple experiment to learn a sinusoid and its first derivative.
Details
- Title
- Learning functions and their derivatives using Taylor series and neural networks
- Authors/Creators
- T. Hanselmann (Author/Creator) - The University of Western AustraliaA. Zaknich (Author/Creator) - The University of Western AustraliaY. Attikiouzel (Author/Creator) - The University of Western Australia
- Publication Details
- IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339), Vol.1, pp.409-412
- Conference
- International Joint Conference on Neural Networks, IJCNN 99 (Washington, DC, USA, 10/07/1999–16/07/1999)
- Publisher
- IEEE
- Identifiers
- 991005541910407891
- Copyright
- © 1999 IEEE
- Murdoch Affiliation
- Murdoch University
- Language
- English
- Resource Type
- Conference paper
Metrics
223 File views/ downloads
144 Record Views