I am a PhD candidate in Computer Science at Case Western Reserve University. My academic pursuits reflect my interest in making computers act more intelligently. As an undergraduate, I studied Computer Science and Cognitive Science with a minor in Artificial Intelligence. I am currently studying various topics in Machine Learning with my advisor, Dr. Soumya Ray.
My current research projects are related to multiple-instance (MI) learning, a generalization of supervised learning in which entire multi-sets (“bags”) of instances have a single label. For example, an image tagged with the label “cat” might contain a set of objects, only one of which is a cat. I am exploring the theoretical and practical consequences of treating these bags as samples from distributions rather than as finite sets. Under this novel generative framework with some additional weak assumptions, my recent work shows that it is possible to learn to label individual instances (e.g., objects within an image) from bag-level label information using traditional supervised learning approaches.
During summer 2012, I was an intern with the Machine Learning and Instrument Autonomy (MLIA) Group at JPL as part of the JPL Graduate Fellowship program. I studied the application of unsupervised and active learning to characterizing sources of radio frequency interference observed by radio telescopes.
During summer 2013, I was an intern at the Max Planck Institute for Intelligent Systems in Tübingen, Germany, where I explored the use of kernel-based approaches to conditional independence testing.