Catalog Home Page

Polar backpropagation [artificial neural networks]

Godfrey, K.R.L. and Attikiouzel, Y. (1990) Polar backpropagation [artificial neural networks]. In: 1990 IJCNN International Joint Conference on Neural Networks, 17 - 21 June, San Diego, CA, USA 143-148 vol.3.

[img]
Preview
PDF - Published Version
Download (359kB)
Link to Published Version: http://dx.doi.org/10.1109/IJCNN.1990.137967
*Subscription may be required

Abstract

A polar backpropagation network is developed for solving the polar classification problem. The architecture is a constrained version of general three-layer backpropagation, such that selected weights correspond to physical entities in the problem, namely, the coordinates of the pole. Heuristic knowledge of the problem is implicit in the network constraints. It is emphasized that the network is not as general as backpropagation, but is useful at solving a specific kind of problem which backpropagation can only partially explain. The polar backpropagation network is not suitable to general classification problems, but is useful at solving the polar classification problem because it locates the pole.

Publication Type: Conference Paper
Publisher: IEEE
Copyright: © 1990 IEEE
URI: http://researchrepository.murdoch.edu.au/id/eprint/17931
Item Control Page Item Control Page

Downloads

Downloads per month over past year