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 Abstract: 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 robots. Bio: Read more: http://eecs.oregonstate.edu/colloquium/efficient-lifelong-machine-learni... [1] [1] http://eecs.oregonstate.edu/colloquium/efficient-lifelong-machine-learning-online-multi-task-learning-perspective
_______________________________________________ Colloquium mailing list Colloquium@ENGR.ORST.EDU https://secure.engr.oregonstate.edu/mailman/listinfo/colloquium
