Institute to Host Data Science Initiative (DSI) Colloquium: Mikhail Belkin, “Radial Basis Function Networks Unshackled”

Thursday, October 13, 2016
2:00 PM – 4:00 PM
Refreshments to follow
Hariri Institute for Computing
111 Cummington Mall, Room 180

The Hariri Institute for Computing will be hosting Mikhail Belkin (Associate Professor, Departments of Computer Science, Engineering & Statistics, Ohio State University) for a Data Science Initiative (DSI) Colloquium. Professor Belkin will speak about “Radial Basis Function Networks Unshackled” on Thursday, October 13, 2016 at 2:00 PM in the Hariri Institute Seminar Room, 111 Cummington Mall.

Abstract: Radial Basis Function (RBF) networks are a classical family of algorithms for supervised learning. The most popular approach for training RBF networks has relied on kernel methods using regularization based on a norm in a Reproducing Kernel Hilbert Space (RKHS), leading to algorithms such as Support Vector Machines, a principled and empirically successful framework for machine learning.

In his talk, Mikhail Belkin will revisit some of the older approaches to training the RBF networks from a modern perspective. He will discuss two common regularization procedures, one based on the square norm of the coefficients in the network and another one using centers obtained by k-means clustering, for it turns out that both of these methods can be recast in terms of a certain data-dependent kernels. He will also provide a theoretical analysis of these methods as well as a number of experimental results, pointing out very competitive experimental performance as well as certain advantages over the standard kernel methods in terms of both flexibility (incorporating of unlabeled data) and computational complexity.

In this context, Belkin will also discuss ideas for scaling these methods to cope with large modern data.  Finally, his results will shed light on some impressive recent successes of using soft k-means features for image recognition and other tasks.

Belkin’s talk is based on joint work with Qichao Que.

Bio: Mikhail Belkin is an Associate Professor in the departments of Computer Science and Engineering and Statistics at the Ohio State  University. He received a PhD  in mathematics from the University of Chicago. His research focuses on understanding structure in data, the principles of recovering these structures and their computational, mathematical and statistical properties. His well-known work includes algorithms such as Laplacian Eigenmaps and Manifold Regularization which use ideas of classical differential geometry for analyzing non-linear high-dimensional data. He is a recipient of an NSF Career Award and has served on editorial boards of the Journal of Machine Learning Research and IEEE PAMI.