The MIT Probabilistic Computing Project aims to build software and hardware systems that augment human and machine intelligence. We are currently focused on probabilistic programming. Probabilistic programming is an emerging field that draws on probability theory, programming languages, and systems programming to provide concise, expressive languages for modeling and general-purpose inference engines that both humans and machines can use.
Our research projects include BayesDB and Picture, domain-specific probabilistic programming platforms aimed at augmenting intelligence in the fields of data science and computer vision, respectively. BayesDB, which is open source and in use by organizations like the Bill & Melinda Gates Foundation and JPMorgan, lets users who lack statistics training understand the probable implications of data by writing queries in a simple, SQL-like language. Picture, a probabilistic language being developed in collaboration with Microsoft, lets users solve hard computer vision problems such as inferring 3D models of faces, human bodies and novel generic objects from single images by writing short (<50 line) computer graphics programs that generate and render random scenes. Unlike bottom-up vision algorithms, Picture programs build on prior knowledge about scene structure and produce complete 3D wireframes that people can manipulate using ordinary graphics software. The core platform for our research is Venture, an interactive platform suitable for teaching and applications in fields ranging from statistics to robotics.
Watch a video of Vikash's MIT Media Lab talk on Probabilistic Programming for Augmented Intelligence for a longer introduction to our research and goals.
September 2016: We are offering an MIT course, 9.S915, Introduction to Probabilistic Programming.
May 2016: BayesDB 0.1.8 is now available.
April 2016: We will be participating in the Healthy Birth, Growth, and Development Knowledge Integration convening in Seattle, organized by the Bill and Melinda Gates Foundation.
March 2016: Video of our Media Lab talk on Probabilistic Programming for Augmented Intelligence is now available.
March 2016: BayesDB 0.1.7 is now available.
March 2016: We are developing a short online course on probabilistic programming and augmented intelligence. Contact our program manager if you’re interested in participating.
February 2016: BayesDB 0.1.6 is now available.
January 2016: Venture Alpha 0.5 is now available.
January 2016: Empirical Systems, Inc., our first spin-out company, has secured seed financing from backers including Matrix Partners and Flybridge Capital.
January 2016: We are offering an MIT IAP course on probabilistic programming for data analysis. It will cover BayesDB, Picture, some Venture, and material on AI from our talk at the MIT ILP Seminar on Minds, Machines, and Management in Vienna (March 2016). Contact our program manager if you’re interested in participating.
January 2016: BayesDB 0.1.5 is now available.
January 2016: We are delighted to be presenting on BayesDB at the Northeast Database Day hosted by the CSAIL Big Data Initiative.
September 2016: Invited tutorial on probabilistic programming at the Machine Learning for Signal Processing Workshop in Salerno, Italy.
For non-technical users, BayesDB makes it possible to query the probable implications of data, build baseline models, and assess inference credibility without training in statistics. BayesDB also lets statisticians easily build complex models that combine semi-parametric Bayes, machine learning, computer simulations, and qualitative (in)dependencies specified by domain experts.
Picture: a probabilistic programming language for computer vision. [CVPR 2015 Paper PDF, best student paper (honorable mention).]
For a full list of papers, technical reports, and conference presentations, please see our publications page.
The ProbComp Reading List serves as a shared basis of knowledge for the project.
Vikash K. Mansinghka
|Vikash Mansinghka is a research scientist at MIT, where he leads the Probabilistic Computing Project. Vikash holds S.B. degrees in Mathematics and in Computer Science from MIT, as well as an M.Eng. in Computer Science and a PhD in Computation. He also held graduate fellowships from the National Science Foundation and MIT's Lincoln Laboratory. His PhD dissertation on natively probabilistic computation won the MIT George M. Sprowls dissertation award in computer science, and his research on the Picture probabilistic programming language won an award at CVPR. He co-founded a venture-backed startup based on this research that was acquired by Salesforce.com, was an advisor to Google DeepMind, and is a co-founder of Empirical Systems, a new venture-backed AI startup aimed at improving the credibility and transparency of statistical inference. He served on DARPA's Information Science and Technology advisory board from 2010-2012, and currently serves on the editorial boards for the Journal of Machine Learning Research and the journal Statistics and Computation.|
The MIT Probabilistic Computing Project is hosted by MIT's Computer Science and Artificial Intelligence Laboratory and Department of Brain and Cognitive Sciences.
Our work is generously supported by research contracts with DARPA (under the XDATA and PPAML programs), the Office of Naval Research and the Army Research Laboratory, and Shell Oil, as well as gifts from Analog Devices and Google. The views expressed on this website and in our research are our own, and do not necessarily reflect the views of our government or corporate sponsors.