I'm Sumit Basu, a Principal Researcher in the Medical Devices Group at Microsoft Research, Redmond. My research focus is on developing interactive, machine-learning based power tools to assist users in understanding and extracting answers from complex data - physiological signals, teaching material/textbooks, computer systems, auditory signals like speech or music, scientific data, document collections, or the web. These power tools sometimes work by observing a user as they perform a task, then assisting them in their efforts once it understands what's going on; in other cases (as in teaching) they provide inputs to the user and adaptively refine their strategy based on what works best. The interactive aspect comes from having humans in a tight loop with the learning algorithm: instead of getting a big batch of labeled data, interactive learning tasks involve a delicate dance between the human and the algorithm to achieve sufficient performance with a minimum of operator effort. These days, I'm particularly interested in how we can use such technologies to detect, analyze, and derive insights from physiological signals with the goal of helping patients monitor and improve their cardiovascular health. This is a deep and complex area, involving problems in signal processing, signal quality estimation, real-time classification, and data mining, as well as fundamental aspects of cardiovascular physiology. If you're a bright graduate student interested in such problems and curious about internship opportunities, drop me a line! a brief bio