Title :
A soft-competitive splitting rule for adaptive tree-structured neural networks
Author :
Perrone, Michael P.
Author_Institution :
Dept. of Phys., Brown Univ., Providence, RI, USA
Abstract :
An algorithm for generating tree structured neural networks using a soft-competitive recursive partitioning rule is described. It is demonstrated that this algorithm grows robust, honest estimators. Preliminary results on a 10-class, 240-dimensional optical character recognition classification task show that the tree outperforms backpropagation. Arguments are made that suggest why this should be the case. The connection of the soft-competitive splitting rule to the twoing rule is described
Keywords :
neural nets; optical character recognition; adaptive tree-structured neural networks; optical character recognition classification; recursive partitioning rule; soft-competitive splitting rule; Adaptive systems; Backpropagation algorithms; Data mining; Interference; Jacobian matrices; Neural networks; Partitioning algorithms; Physics; Robustness; Training data;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227094
