7:00 PM, Thursday, 7 December 2017
MIT Room 32-G449 (Kiva)
Theo Giannakopoulos, BAE Systems
In this talk I will present a rapidly maturing approach to machine learning and data science called probabilistic programming. Probabilistic programming languages enable the use of machine learning by programmers and domain specialists without experience in the creation of specialized machine learning algorithms. However, the combination of probability and program semantics makes reasoning about probabilistic programs challenging, even for probabilistic programming language implementers. I will outline an approach to reasoning about probabilistic programs using techniques from traditional programming language theory.
Theo Giannakopoulos is a Principal Research Engineer at BAE Systems. He led the development of the Tempest programming language for BAE's SAFE project on the DARPA CRASH program and was the Principal Investigator for BAE's Open Probabilistic Programming Platform project for the DARPA PPAML program. Prior to joining BAE Systems, he developed secure back-office systems for financial and e-commerce companies. He received his Master's degree in Computer Science at Worcester Polytechnic Institute (WPI) as part of the Applied Logic and Security group under the supervision of Prof. Daniel Dougherty, researching languages for the formal specification of security policies and policy combinators.
This joint meeting of the Boston Chapters of the IEEE Computer and GRSS Societies and GBC/ACM will be held in MIT Room 32-G449 (the Kiva conference room on the 4th floor of the Stata Center, buildng 32 on MIT maps) .  You can see it on this map of the MIT campus.
Up-to-date information about this and other talks is available online at http://ewh.ieee.org/r1/boston/computer/. You can sign up to receive updated status information about this talk and informational emails about future talks at http://mailman.mit.edu/mailman/listinfo/ieee-cs, our self-administered mailing list.
Updated: Oct 30, 2017.