Toward a Computational Model of Transfer

Daniel Oblinger

Abstract


This article focuses on a broad framing of the DARPA Transfer Learning Program research and an assessment of its progress, limitations, and challenges, from an admittedly personal but DARPA-influenced perspective. I will focus on a broad framing of TL that that will allow us to talk about this body of work as a whole, and use this to look towards work yet to be done in this area. I will consider both indicated application areas for transfer learning, as well as indicated future research challenges. With each of these I will also venture assessment of the "ripeness" of each of these subareas for follow on work-of course this assessment will be a very personal estimation based on the effort and progress made during the TL program.

Full Text:

PDF


DOI: http://dx.doi.org/10.1609/aimag.v32i2.2337

Copyright © 2014, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.