Sciweavers

ICPR
2002
IEEE

Graph of Neural Networks for Pattern Recognition

15 years 18 days ago
Graph of Neural Networks for Pattern Recognition
This paper presents a new architecture of neural networks designed for pattern recognition. The concept of induction graphs coupled with a divide-and-conquer strategy defines a Graph of Neural Network (GNN). It is based on a set of several little neural networks, each one discriminating only two classes. The principles used to perform the decision of classification are : a branch quality index and a selection by elimination. A significant gain in the global classification rate can be obtained by using a GNN. This is illustrated by tests on databases from the UCI machine learning database repository. The experimental results show that a GNN can achieve an improved performance in classification.
Hubert Cardot, Olivier Lezoray
Added 09 Nov 2009
Updated 09 Nov 2009
Type Conference
Year 2002
Where ICPR
Authors Hubert Cardot, Olivier Lezoray
Comments (0)