ICML-98 Submission #63

Using Knowledge Transfer for Prognostic Prediction

Author: 
W. Nick Street
Computer Science Department
Oklahoma State University
Stillwater, OK 74078
email: {\tt nstreet@cs.okstate.edu}
(405) 744-6471

Abstract: 

An important and difficult prediction task in many domains,
particularly medical decision making, is that of prognosis.  Prognosis
presents a unique set of problems to a learning system when some of
the outputs are unknown.  This paper presents a new approach to
prognostic prediction, using ideas from nonparametric statistics to
fully utilize all of the available information in a neural
architecture.  Functional knowledge transfer is used to separate the
problem into a sequence of learning tasks, all of which share a common
learned internal representation.

Keywords: artificial neural networks, knowledge transfer, survival data