Robust Linear Discriminant Trees
			    George H. John
		     Computer Science Department
			 Stanford University
			  Stanford, CA 94305
			gjohn@cs.Stanford.EDU


We present a new method for the induction of classification trees with
linear discriminants as the partitioning function at each internal
node.  This paper presents two main contributions: first, a novel
objective function called soft entropy which is used to identify
optimal coefficients for the linear discriminants , and second, a novel
method for removing outliers called iterative re-filtering
which boosts performance on many datasets.  These two ideas are
presented in the context of a single learning system called DT-SEPIR,
which is compared with the CART and OC1 algorithms.


Citation:

George H. John.  Robust linear discriminant trees.  In D. Fisher and
H. Lenz, editors, _Learning From Data: Artificial Intelligence and
Statistics V_, Lecture Notes in Statistics, Chapter 36, pages
375--385. Springer-Verlag, New York, 1996.