Decision boundary modelling-a constructive algorithm for high precision real world data models

A network's generalisation is extrapolated from the training examples, i.e. it is defined by the network's model of the training data. Simplifying this model will increase the resistance to noise, inherent in the training data, but will also lose information which may not be noise. This pa...

Full description

Saved in:
Bibliographic Details
Published inIJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339) Vol. 5; pp. 3114 - 3118 vol.5
Main Authors McLean, D., Bandar, Z., O'Shea, J.D.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1999
Subjects
Data models
Entropy
Intelligent systems
Interpolation
Mathematics
Network topology
Neural networks
Neurons
Shape
Training data
Online AccessGet full text

Cover

More Information
Summary:A network's generalisation is extrapolated from the training examples, i.e. it is defined by the network's model of the training data. Simplifying this model will increase the resistance to noise, inherent in the training data, but will also lose information which may not be noise. This paper discusses the use of Voronoi tessellations for highly detailed data models and the effects of noise. An original algorithm is developed for constructing a competitive layer of k-nearest neighbour type neurons. These neurons are trained to model the decision boundaries and therefore approximate the perfect bisector that is required. The new algorithm is empirically compared with three existing hyperplanic algorithms-neural tree network (NTN), backpropagation (BP), and the entropy net, on three real world continuous data sets.
ISBN:0780355296
9780780355293
ISSN:1098-7576
1558-3902
DOI:10.1109/IJCNN.1999.836148