AIC Seminar Series

Most research in machine learning focuses on a rather narrow definition of training example. Commonly, the learning algorithm is simply given a list of "input-output" (I/O) pairs. From these, the task of the machine learner is to induce a function that correctly replicates all, or at least most, of these training examples (and in addition accurately predicts the output for inputs not seen during training). However, a much richer sense of training example is possible, one where the teacher provides broadly applicable information, rather than just specific cases. We present our recent work on creating Knowledge-Based Support Vector Machines, which are able to accept instruction beyond input-output pairs. Since the learning algorithm is allowed to accept, refine, or discard this instruction, we view the instruction as advice, as opposed to commands, which computers must literally follow. We also discuss how the advice-taking approach can be applied to transfer learning; in this case, an algorithm automatically creates advice for a new task by analyzing what was learned on a similar, prior task.

Jude Shavlik is a Professor of Computer Sciences and of Biostatistics and Medical Informatics at the University of Wisconsin - Madison, and is a Fellow of the American Association for Artificial Intelligence. He has been at Wisconsin since 1988, following the receipt of his PhD from the University of Illinois for his work on Explanation-Based Learning. His current research interests include machine learning and computational biology, with an emphasis on using rich sources of training information, such as human-provided advice. He served for three-years as editor-in-chief of the AI Magazine and serves on the editorial board of about a dozen journals. He chaired the 1998 International Conference on Machine Learning, co-chaired the First International Conference on Intelligent Systems for Molecular Biology in 1993, co-chaired the First International Conference on Knowledge Capture in 2001, was conference chair of the 2003 IEEE Conference on Data Mining, and will be co-chairing the 2007 International Conference on Inductive Logic Programming. He was a founding member of both the board of the International Machine Learning Society and the board of the International Society for Computational Biology. He co-edited, with Tom Dietterich, "Readings in Machine Learning." His research has been supported by DARPA, NSF, NIH, ONR, DOE, AT&T, IBM, and NYNEX.