Transfer Learning Progress and Potential

84 AI MAGAZINE As evidenced by the articles in this special issue, transfer learning has come a long way in the past five or so years, partially because of DARPA’s Transfer Learning program, which sponsored much of the work reported in this issue.1 Work conducted as part of this program and work conducted under other auspices, as evidenced by the many conference and workshop papers,2 demonstrates the interest and promise in this approach to building intelligent agents. There is a Transfer Learning Toolkit for Matlab available on the web.3 Transfer learning has developed techniques for classification, regression, and clustering (as summarized in Pan and Yang’s 2009 survey) and for complex interactive tasks that are often best addressed by reinforcement learning techniques. And transfer learning has been applied to domains as diverse as named entity recognition, image clustering, information retrieval, link prediction, AP physics, and others. As with many human-level AI goals, transfer learning is still a long way from the ability for agents to take advantage of relevant previous learned knowledge and experience to perform (at least) competently and effectively on new tasks the first time they are encountered. However, there is a more practical and more feasible goal for transfer learning against which progress is being made. An engineering-oriented goal of artificial intelligence that could be enabled by transfer learning is the ability to construct a large number of diverse applications not from scratch, but by taking advantage of knowledge already acquired and formally represented for other purposes. This would be useful when knowledge acquisition is expensive, when sufficient amounts of training data for a new task are unavailable, or when the new task must be learned more rapidly than possible from directly relevant training data.