Clustering Learning Tasks and the Selective Cross-Transfer of Knowledge

May 1998

Clustering Learning Tasks and the Selective Cross-Transfer of Knowledge

Authors:

Sebastian Thrun and Joseph O'Sullivan

Abstract:

Recently, there has been an increased interest in machine learning methods that transfer knowledge across multiple learning tasks and “learn to learn.” Such methods have repeatedly been found to outperform conventional, single-task learning algorithms when the learning tasks are appropriately related. To increase robustness of such approaches, methods are desirable that can reason about the relatedness of individual learning tasks, in order to avoid the danger arising from tasks that are unrelated and thus potentially misleading.

This paper describes the task-clustering (TC) algorithm. TC clusters learning tasks into classes of mutually related tasks. When facing a new learning task, TC first determines the most related task cluster, then exploits information selectively from this task cluster only. An empirical study carried out in a mobile robot domain shows that TC outperforms its non-selective counterpart in situations where only a small number of tasks is relevant.
@incollection{Thrun-1998-16514,
author = {Sebastian Thrun And Joseph O'Sullivan},
title = {Clustering Learning Tasks and the Selective Cross-Transfer of Knowledge},
booktitle = {Learning To Learn},
publisher = {Kluwer Academic Publishers},
editor = {S. Thrun and L. Pratt},
year = {1998},
month = {May},
pages = {235 - 257},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.