Efficient Lifelong Machine Learning: an Online Multi-Task Learning
Perspective is coming at 03/07/2018 - 9:00am

KEC 1007
Wed, 03/07/2018 - 9:00am

Eric Eaton
Non-tenure track faculty member, Department of Computer and Information
Science, University of Pennsylvania

Lifelong learning is a key characteristic of human intelligence, largely
responsible for the variety and complexity of our behavior. This process
allows us to rapidly learn new skills by building upon and continually
refining our learned knowledge over a lifetime of experience. Incorporating
these abilities into machine learning algorithms remains a mostly unsolved
problem, but one that is essential for the development of versatile
autonomous systems. In this talk, I will present our recent progress in
developing algorithms for lifelong machine learning for classification,
regression, and reinforcement learning, including applications to perception
and optimal control for robotics. These algorithms approach the problem from
an online multi-task learning perspective, acquiring knowledge incrementally
over consecutive learning tasks, and then transferring that knowledge to
rapidly learn to solve new tasks. Our approach is highly efficient, scaling
to large numbers of tasks and amounts of data, and provides a variety of
theoretical guarantees. I will also discuss our work toward automatic
cross-domain transfer between diverse tasks, zero-shot transfer learning from
task descriptions, and applications of these methods to autonomous service


Read more:

Colloquium mailing list

Reply via email to