The goal of this seminar is to familiarize students with fundamental concepts and paradigms in computational learning, and to discuss their assumptions, applicability, and relevance to issues of concern to linguists.
In terms of the organization of topics, I begin with unsupervised learning (EM, clustering), then segue into feature-based representations and stochastic optimization (LSA, genetic algorithms). From there we move to a series on classification/concept learning from labeled instances (neural networks, PAC learning, SVMs), then probabilistic modeling (Bayesian inference, MDL, maximum entropy), and finally to Gold's paradigm and grammatical inference.
I'm looking forward to a semester in which we strengthen our ability to discuss language-related learning issues in more formal, computational terms, and then apply that ability in open-minded discussions that lead to creative research ideas and innovative final projects.
Philip Resnik, Associate Professor
Department of Linguistics and Institute for Advanced Computer Studies
Department of Linguistics
1401 Marie Mount Hall UMIACS phone: (301) 405-6760
University of Maryland Linguistics phone: (301) 405-8903
College Park, MD 20742 USA Fax: (301) 314-2644 / (301) 405-7104
http://umiacs.umd.edu/~resnik E-mail: resnik AT umd _DOT.GOES.HERE_ edu