Catalog Home Page

Learning functions and their derivatives using Taylor series and neural networks

Hanselmann, T., Zaknich, A. and Attikiouzel, Y. (1999) Learning functions and their derivatives using Taylor series and neural networks. In: International Joint Conference on Neural Networks, IJCNN 99, 10 - 16 July, Washington, DC, USA pp. 409-412.

[img]
Preview
PDF - Published Version
Download (374kB)
Link to Published Version: http://dx.doi.org/10.1109/IJCNN.1999.831529
*Subscription may be required

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.

Publication Type: Conference Paper
Publisher: IEEE
Copyright: © 1999 IEEE
URI: http://researchrepository.murdoch.edu.au/id/eprint/19694
Item Control Page Item Control Page

Downloads

Downloads per month over past year