【Topic】IEEE Distinguished Lecture: Recent Development in Generalization

Error for Supervised Learning Problem with Applications in Model Selection and Feature Selection

【Speaker】Daniel Yeung

【Time】2008-10-21, 10:30 am

【Venue】Room 418, ShunDe Building, School of Economics and Management,

Tsinghua University

【Abstract】Generalization error model provides a theoretical support for a classifier's performance in terms of prediction accuracy. However, existing models give very loose error bounds. This explains why classification systems generally rely on experimental validation for their claims on prediction accuracy. In this talk we will revisit this problem and explore the idea of developing a new generalization error model based on the assumption that only prediction accuracy on unseen points in a neighbourhood of a training point will be considered, since it will be unreasonable to require a classifier to accurately predict unseen points "far away" from training samples. The new error model makes use of the concept of sensitivity measure for an ensemble of multiplayer feedforward neural networks (Multilayer Perceptrons or

Radial Basis Function Neural Networks). Two important applications will be demonstrated, model selection and feature reduction for RBFNN classifiers. A number of experimental results using datasets such as the UCI, the 99 KDD Cup, and text categorization, will be presented.

【About the speaker】Daniel S. Yeung received his Ph.D. in Applied Mathematics from the Case Western Reserve University. He is the President of the IEEE Systems, Man and Cybernetics (SMC) Society, a Fellow of the IEEE and an IEEE Distinguished Lecturer. His current research interests include neural-network sensitivity analysis, data mining, Chinese computing, and fuzzy systems.

He was an associate editor for both IEEE Transactions on Neural Networks and IEEE Transactions on SMC (Part B), and for the International Journal on Wavelet and Multiresolution Processing. He was a member of the Board of Governor, Vice President for Technical Activities, and Vice President for Long Range Planning and Finance for the IEEE SMC Society. He is also the founding Chairman of the IEEE SMC Hong Kong Chapter.

His past teaching and academic administrative positions include a Chair Professor and Head at Department of Computing, the Head of the Management Information Unit at the Hong Kong Polytechnic University, Associate Head/Principal Lecturer at the Department of Computer Science, City Polytechnic of Hong Kong, a tenured Assistant Professor at the School of Computer Science and Technology and Assistant Professor at the Department of Mathematics, both at Rochester Institute of Technology.