Peter Stone's Selected Publications

Classified by TopicClassified by Publication TypeSorted by DateSorted by First Author Last NameClassified by Funding Source


Transfer Learning and Intelligence: an Argument and Approach

Matthew E. Taylor, Gregory Kuhlmann, and Peter Stone. Transfer Learning and Intelligence: an Argument and Approach. In Proceedings of the First Conference on Artificial General Intelligence, March 2008.
AGI-2008
Google video version of the conference presentation.

Download

[PDF]149.0kB  [postscript]202.5kB  

Abstract

In order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. Classical machine learning techniques have had many significant empirical successes, but large real-world problems that are of interest to generally intelligent agents require learning much faster (with much less training experience) than is currently possible. This paper presents transfer learning, where knowledge from a learned task can be used to significantly speed up learning in a novel task, as the key to achieving the learning capabilities necessary for general intelligence. In addition to motivating the need for transfer learning in an intelligent agent, we introduce a novel method for selecting types of tasks to be used for transfer and empirically demonstrate that such a selection can lead to significant increases in training speed in a two-player game.

BibTeX Entry

@InProceedings(AGI08-taylor,
        author="Matthew E.\ Taylor and Gregory Kuhlmann and Peter Stone",
        title="Transfer Learning and Intelligence: an Argument and Approach",
        booktitle="Proceedings of the First Conference on Artificial General Intelligence",
        month="March",
        year="2008",
        abstract="In order to claim fully general intelligence in an
          autonomous agent, the ability to learn is one of the most
          central capabilities.  Classical machine learning techniques
          have had many significant empirical successes, but large
          real-world problems that are of interest to generally
          intelligent agents require learning much faster (with much
          less training experience) than is currently possible. This
          paper presents \emph{transfer learning}, where knowledge
          from a learned task can be used to significantly speed up
          learning in a novel task, as the key to achieving the
          learning capabilities necessary for general intelligence. In
          addition to motivating the need for transfer learning in an
          intelligent agent, we introduce a novel method for selecting
          types of tasks to be used for transfer and empirically
          demonstrate that such a selection can lead to significant
          increases in training speed in a two-player game.",
        wwwnote={<a href="http://agi-08.org/">AGI-2008</a><br>Google video version of <a href="http://video.google.com/videoplay?docid=1984013763155542745&hl=en">the conference presentation</a>.},
)

Generated by bib2html.pl (written by Patrick Riley ) on Wed Sep 24, 2014 22:15:11