Date: Friday, November 8 Location: Maxwell-Dworkin G115, 33 Oxford Street, Cambridge, MA 02138 Speaker: Ben Vigoda, Director, Analog Devices Lyric Labs Time: Informal lunch with speaker, 12:30pm; Talk, 1:00pm. Title: Probabilistic Programming and Probability Processing Abstract: We are developing a computing stack for Bayesian inference and machine learning, including integrated circuits, probabilistic programming languages, compilers, and applications. Our first probability processor hardware demonstrates orders of magnitude wins on machine learning and statistical inference benchmarks. We are developing open-source probability programming languages that help enable rapid prototyping and development of statistical machine learning applications. We will demonstrate some applications that we are building on top of the probability processing stack. Speaker bio: Ben Vigoda is the director of Analog Devices Lyric Labs, a corporate research lab located in Kendall Square, Cambridge that grew from the acquisition by Analog Devices of Lyric Semiconductor, Inc. Lyric was selected as one of the 50 Most Innovative Companies by Technology Review in 2010. The company's work on probability processors has been featured in the Wall Street Journal, New York Times, Wired, and EE Times. ************************* Upcoming IACS Seminar The final IACS seminar of the fall semester will be held on Friday, 11/22. Hugo Larochelle, Assistant Professor at the Université de Sherbrooke, will present on "Deep Learning for Distribution Estimation." Please visit http://iacs.seas.harvard.edu/events to subscribe to our Google calendar, manage your subscription to this mailing list, or access video and audio recordings of previous seminars. ************************* Another upcoming event that may be of interest: The third workshop for Software Institute for Methodologies and Abstractions for Codes (SIMAC) Numerical Algorithm for Extreme Computing Architectures November 4-5, 2013 at Boston University http://blogs.bu.edu/simac3/ Sponsored by Center for Computation & Technology -- LSU Center of Computational Science -- BU Hariri Institute for Computing and Computational Science & Engineering -- BU This third SIMAC workshop will focus on the design of Numerical Algorithms and Software Frameworks to accommodate the increasingly complex environment of multiscale physics and complex heterogeneous HPC architectures. Algorithmic examples include Multigrid(MG), Domain Decomposition(DD)solvers and Adaptive Mesh Refinement(AMR). Hardware examples include GPU and PHI heterogeneous architectures. The goal is to explore existing collaborative teams and frameworks that seek to respond to this disruptive technological landscape and suggest new or improved methods required to keep pace with the evolution of Extreme scale computing. Registration (no fee), travel/lodging suggestions and agenda are found on the following page: http://blogs.bu.edu/simac3/ _______________________________________________ Iacs-events mailing list Iacs-events(a)seas.harvard.edu https://lists.seas.harvard.edu/mailman/listinfo/iacs-events