BIOGRAPHY
My research interests focus on artificial intelligence and statistics, particularly the area of machine learning and related fields like pattern recognition, information theory, and neural networks. In general, machine learning is concerned with computer programs that automatically improve their performance through experience. The goal is to investigate the theoretical foundations of learning and to develop adaptive systems that can take advantage of observations and examples for solving a variety of tasks. This problem has many facets such as learning concepts and general rules based on a set of training examples (inductive inference), learning functional dependencies between variables (regression, prediction), learning probabilistic models or probability densities from data, automatically extracting structured representations from data sets, and learning from experience for optimal planing and decision making.
Recent interests include: kernel-based methods for classification and density estimation, differential geometry and statistics, combining labeled and unlabeled data in classification, methods for dimension reduction and data clustering, approximation methods for learning and inference in graphical models, and information-theoretic models for multiagent systems. The major application domains I have been working on are data analysis, information retrieval, computer vision, natural language processing, and robotics. Recent work deals with text learning and information retrieval, stochastic models for the Web, object recognition and image retrieval, as well as user modeling and collaborative filtering.
I received an undergraduate degree and a doctorate degree in Computer Science from the University of Bonn, Germany. Before coming to Brown in 1999 I spent two years as a postdoc at MIT and at UC Berkeley.
|
