CAM colloquium - Friday, April 18
3:30 p.m.
655 Rhodes Hall

Speaker: Jennifer Dy, Northeastern

 

Title: Non-Redundant Multi-View Clustering

 

Abstract: Many existing databases (e.g., image, text document, web pages) are characterized by high dimensions and are unlabeled. It is easier to learn to recognize or associate phenomena if provided a bunch of examples labeled by an expert, but as the volume of data increases, the ability of experts to do such labeling becomes limited. In some cases, labeling isimpossible because the phenomena are not known or are yet to be discovered. Thus there is an increasing need to develop algorithms, which can learn without such training (called unsupervised learning). This technique, called clustering, is the process of grouping similar objects/samples together. Typical clustering algorithms output a single clustering of the data. However, in real world applications, data can often be interpreted in many different ways; data can have different groupings that are reasonable and interesting from different perspectives. This is especially true for high-dimensional data, where different feature subspaces may reveal different structures of the data. Why commit to one clustering solution while all these alternative clustering views might be interesting to the user. In this talk I first provide different ways of finding clusters hidden in high dimensional spaces and then present a new clustering paradigm for exploratory data analysis: find all non-redundant clustering views of the data, where data points of one cluster can belong to different clusters in other views.

In the final part of my talk, I present other research projects in our group. In particular, I will talk about a modified support vector machine formulation that takes correlation among samples into account, and applications of machine learning to tracking lung tumor in radiotherapy treatment and to 3D confocal skin image segmentation.

Biography:
Dr. Jennifer G. Dy is an assistant professor at the Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, since 2002. She obtained her MS and PhD in 1997 and 2001 respectively from the School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, and her BS degree in 1993 from the Department of Electrical Engineering, University of the Philippines. She received an NSF Career award in 2004. She is an action editor for the journal, "Machine Learning" since 2007, and publications chair for the "International Conference on Machine Learning" in 2004. Her research interests include Machine Learning, Data Mining, Statistical Pattern Recognition, and Medical Image Analysis.

Refreshments at 4:30 in 657 Rhodes Hall.