Unsupervised Splitting Rules for Neural Tree Classifiers
Abstract
This paper presents two unsupervised neural network splitting rules for use with CART-like neural tree algorithms in high dimensional data space. These splitting rules use an adaptive variance estimate to avoid some possible local minima which arise in unsupervised methods. We explain when the unsupervised splitting rules outperform supervised neural network splitting rules and when the unsupervised splitting rules outperform the standard node impurity splitting rules of CART. Using these unsupervised splitting rules lead to a nonparametric classifier for high dimensional space that extracts local features in an optimized way.... CART, Unsupervised feature extraction, Neural trees.
Document Details
- Document Type
- Technical Report
- Publication Date
- May 17, 1993
- Accession Number
- ADA264961
Entities
People
- Michael P. Perone
- Nathan Intrator
Organizations
- Brown University