Logo image
Polar backpropagation [artificial neural networks]
Conference paper   Open access

Polar backpropagation [artificial neural networks]

K.R.L. Godfrey and Y. Attikiouzel
1990 IJCNN International Joint Conference on Neural Networks, pp.143-148 vol.3
IEEE
1990 IJCNN International Joint Conference on Neural Networks (San Diego, CA, USA, 17/06/1990–21/06/1990)
1990
pdf
polar_backpropagation.pdfDownloadView
Published (Version of Record) Open Access
url
Link to Published Version *Subscription may be requiredView

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.

Details

Metrics

150 File views/ downloads
86 Record Views
Logo image