Towards Interpretable Explanations for Transfer Learning in Sequential Tasks
Name
AAAI-SSS16_FinalPaper.pdf
Size
195.59 KB
Format
Adobe PDF
Checksum (MD5)
771d3b42d024f1eb84d6501c37d8b387
Author(s)
Ramakrishnan, Ramya
Shah, Julie A
Date Issued
March 2016
Journal
AAAI 2016 Spring Symposium
Publisher
Association for the Advancement of Artificial Intelligence
Citation
Ramakrishnan, Ramya and Julie Shah. "Towards Interpretable Explanations for Transfer Learning in Sequential Tasks." AAAI Spring Symposium, March 21-23, 2016, Palo Alto, CA.
Version
Author's final manuscript
Abstract
People increasingly rely on machine learning (ML) to make intelligent decisions. However, the ML results are often difficult to interpret and the algorithms do not support interaction to solicit clarification or explanation. In this paper, we highlight an emerging research area of interpretable explanations for transfer learning in sequential tasks, in which an agent must explain how it learns a new task given prior, common knowledge. The goal is to enhance a user’s ability to trust and use the system output and to enable iterative feedback for improving the system. We review prior work in probabilistic systems, sequential decision-making, interpretable explanations, transfer learning, and interactive machine learning, and identify an intersection that deserves further research focus. We believe that developing adaptive, transparent learning models will build the foundation for better human-machine systems in applications for elder care, education, and health care.
MIT Department
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
www.aaai.org/ocs/index.php/SSS/SSS16/paper/download/12757/11967
