Transfer Learning and Intelligence: an Argument and Approach (2008)
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 emphtransfer 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.
In Proceedings of the First Conference on Artificial General Intelligence, March 2008.

Gregory Kuhlmann Ph.D. Alumni kuhlmann [at] cs utexas edu
Peter Stone Faculty pstone [at] cs utexas edu
Matthew Taylor Ph.D. Alumni taylorm [at] eecs wsu edu