MULTITASK LEARNING

Multitask Learning is an approach to inductive transfer that improves generalization by using the domain information contained in the traini ng signals of related tasks as an inductive bias. It does this by lear ning tasks in parallel while using a shared representation; what is le arned For each task can help other tasks be learned better. This paper reviews prior work on MTL, presents new evidence that MTL in backprop nets discovers task relatedness without the need of supervisory signa ls, and presents new results for MTL with k-nearest neighbor and kerne l regression. In this paper we demonstrate multitask learning in three domains. We explain how multitask learning works, and show that there are many opportunities for multitask learning in real domains. We pre sent an algorithm and results for multitask learning with case-based m ethods like k-nearest neighbor and kernel regression, and sketch an al gorithm for multitask learning in decision trees. Because multitask le arning works, can be applied to many different kinds of domains, and c an be used with different learning algorithms, we conjecture there wil l be many opportunities for its use on real-world problems.