OVERVIEW

Humans learn to solve increasingly complex tasks by continually building upon and refining knowledge over a lifetime of experience. This process of continual learning and transfer allows us to rapidly learn new tasks, often with very little training. Over time, it enables us to develop a wide variety of complex abilities across many domains.

Despite recent advances in transfer learning and representation discovery, lifelong machine learning remains a largely unsolved problem. Lifelong machine learning has the huge potential to enable versatile systems that are capable of learning a large variety of tasks and rapidly acquiring new abilities. These systems would benefit numerous applications, such as medical diagnosis, virtual personal assistants, autonomous robots, visual scene understanding, language translation, and many others.

Learning over a lifetime of experience involves a number of procedures that must be performed continually, including:
1.) Discovering representations from raw sensory data that capture higher-level abstractions,
2.) Transferring knowledge learned on previous tasks to improve learning on the current task,
3.) Maintaining the repository of accumulated knowledge, and
4.) Incorporating external guidance and feedback from humans or other agents.

Each of these procedures encompasses one or more subfields of machine learning and artificial intelligence. The primary goal of this symposium is to bring together practitioners in each of these areas and focus discussion on combining these lines of research toward lifelong machine learning.



TOPICS

The symposium will include paper presentations, talks, and discussions on a variety of topics related to lifelong learning, including but not limited to:

knowledge transfer
- active transfer learning
- multi-task learning
- cross-domain transfer
- knowledge/schema mapping
- source knowledge selection
- one-shot learning
- transfer over long sequences of tasks

continual learning
- online multi-task learning
- online representation learning
- knowledge maintenance/revision
- developmental learning
- scalable transfer learning
- task/concept drift
- self-selection of tasks

representation discovery
- learning from raw sensory data
- deep learning
- latent representations
- multi-modal/multi-view learning
- multi-scale representations

incorporating guidance from external teachers
- learning from demonstration
- skill shaping
- curriculum-based training
- interactive learning
- corrective feedback
- agent-teacher communication

frameworks for lifelong learning
- architectures
- software frameworks
- testbeds
- evaluation methodology

applications of lifelong learning
- data sets
- application domains/environments
- simulators
- deployed applications

Within these topics, the symposium will explore lifelong learning in different problem formats, including classification, regression, and sequential decision-making problems.



SUBMISSION INSTRUCTIONS

Prospective participants are invited to submit either full-length papers (up to 6 pages) or short papers/extended abstracts (2 pages) in PDF format using the EasyChair conference system: https://www.easychair.org/conferences/?conf=aaaisss13lml.

All submissions should follow AAAI style guidelines. While we encourage original work, we will also consider modified versions or extended abstracts of previously published work, provided it is directly related to the symposium goals and the prior publication is explicitly identified.



IMPORTANT DATES

October 15, 2012 - Submissions due via EasyChair
November 9, 2012 - Notification of acceptance/rejection sent to authors
January 18, 2013 - Final papers and signed distribution license due to AAAI
February 15, 2013 - Invited participants registration deadline
March 8, 2013 - Final (open) registration deadline
March 25-27, 2013 - Symposium at Stanford University, California



ORGANIZING COMMITTEE

Chair:
Eric Eaton (Bryn Mawr College)

Committee Members:
Terran Lane (Google)
Honglak Lee (University of Michigan)
Michael Littman (Brown University)
Fei Sha (University of Southern California)
Thomas Walsh (University of Kansas)