Accessibility navigation


Multi-task learning by pareto optimality

Dyankov, D., Riccio, S. D., Di Fatta, G. and Nicosia, G. (2019) Multi-task learning by pareto optimality. In: Machine Learning, Optimization, and Data Science. LOD 2019. Lecture Notes in Computer Science (11943). Springer, pp. 605-618. ISBN 9783030375997

Full text not archived in this repository.

It is advisable to refer to the publisher's version if you intend to cite from this work. See Guidance on citing.

To link to this item DOI: 10.1007/978-3-030-37599-7_50

Abstract/Summary

Deep Neural Networks (DNNs) are often criticized because they lack the ability to learn more than one task at a time: Multitask Learning is an emerging research area whose aim is to overcome this issue. In this work, we introduce the Pareto Multitask Learning framework as a tool that can show how effectively a DNN is learning a shared representation common to a set of tasks. We also experimentally show that it is possible to extend the optimization process so that a single DNN simultaneously learns how to master two or more Atari games: using a single weight parameter vector, our network is able to obtain sub-optimal results for up to four games.

Item Type:Book or Report Section
Refereed:Yes
Divisions:Faculty of Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
ID Code:89524
Publisher:Springer

University Staff: Request a correction | Centaur Editors: Update this record

Page navigation