Sumit Basu

I received my BS (1995), MEng (1997), and PhD (2002) all from MIT in Electrical Engineering and Computer Science. I did my graduate work at the Media Lab with Professor Alex Pentland. My doctoral thesis, “Conversational Scene Analysis,” examined how machine learning and signal processing techniques could be used to understand the structure of conversational interactions from auditory signals without recognizing words. The common thread through all of my work to date has been the combination of human interaction and machine learning; fortunately there are an endless array of application areas of this ilk, especially if one is flexible in one’s definition of interaction.

I recently joined the Medical Devices Group at Microsoft Research. We’ll have much more to say about the exciting project we’re working on very soon.

Our new paper, “Deep Questions without Deep Understanding”, on a new technique for generating high-level (deep) questions from large spans of text (i.e., entire Wikipedia sections, as opposed to individual sentences), will be appearing in July at ACL 2015.

ML for Physiological Signals: using machine learning to detect, analyze, and derive insights from physiological signals to help patients monitor and improve their cardiovascular health.

Teaching with Machine Learning: using machine learning to help students and teachers of all ages and all types of educational goals achieve their objectives more effectively and efficiently.

Sho (opens in new tab): a powerful interactive environment for scientific computing and prototyping based on IronPython. Find out more and download it here (opens in new tab). Also check out this code for getting real-time skeleton data from Kinect in Sho (opens in new tab).

Songsmith (opens in new tab): a songwriting tool that takes melodies and helps develop accompaniments for them: based on this research (opens in new tab) with Dan Morris, it’s now a product (with much help from the MSR Advanced Development Team). Check it out and download the trial here (opens in new tab). It’s also now free to many educational institutions via MSDN Academic Alliance (opens in new tab) and the Innovative Teachers’ Network (opens in new tab).

StickySorter (opens in new tab): a tool for doing affinity diagramming and other flavors of information organization I developed with Julie Guinn and Office Labs: you can download it here (opens in new tab).

Music Analysis/Synthesis (opens in new tab): using machine learning to help users understand, manipulate, and create music

Systems and Machine Learning: using machine learning to address problems in computer systems

Conversational Scene Analysis: seeking structure and content from conversational patterns

Sponsorship Chair, Intelligent User Interfaces 2015 (IUI’15) (opens in new tab).

Senior PC Member, Intelligent User Interfaces 2009 (IUI’09) (opens in new tab), 2010 (opens in new tab), 2011 (opens in new tab), 2012, 2013, 2014, 2015, 2016.

PC Member, Learning at Scale 2015 (L@S 2015) (opens in new tab).

Co-Chair (with Jonathan Huang and Kalyan Veeramachaneni), DDE 2013: Workshop on Data-Driven Education (opens in new tab) at NIPS 2013.

PC Member, AAAI 2011 NECTAR Track (opens in new tab)

Co-Chair (with Ashish Kapoor), Workshop on Analysis and Design of Algorithms for Interactive Machine Learning (ADA-IML’09) at NIPS 2009.

PC Member, IJCAI’09 (opens in new tab).

Co-Chair (with Armando Fox), Systems and Machine Learning Workshop, 2008 (opens in new tab) (SysML 2008 (opens in new tab)). at OSDI 2008.

Co-Chair (with Archana Ganapathi, Emre Kiciman, and Fei Sha), MLSys’07: Workshop on Statistical Learning Techniques for Systems Problems (opens in new tab) at NIPS 2007.

Publicity Chair, NIPS 2007 (opens in new tab). You can see the poster I designed for the conference here (opens in new tab).

PC Member, Systems and Machine Learning Workshop, 2007 (SysML 2007) (opens in new tab). at NSDI 2007.

For fall quarter 2007, Emre Kiciman and I taught a graduate course on Systems Applications of Machine Learning (cse599n) (opens in new tab) at the University of Washington.

Other quarters, I co-taught the Markovia Seminar (cse590mv) on Machine Learning with Tanzeem Choudhury at the University of Washington.

drawing/painting/illustration (opens in new tab), singing/songwriting (opens in new tab), and clothing design/modification.