*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Tess Malone, Communications Officer
Summary Sentence: Learning as Coding: Program Synthesis for Reliable and Interpretable Artificial Intelligence
Full Summary: No summary paragraph submitted.
Swarat ChaudhuriTITLE: Learning as Coding: Program Synthesis for Reliable and Interpretable
Artificial Intelligence
ABSTRACT:
Program synthesis is the problem of automatically discovering programs that satisfy a specification. While the traditional “home” of the problem is in the Formal Methods community, recent research has discovered certain exciting connections between program synthesis and statistical machine learning. In this talk, I will describe some of these connections, developed in our recent work, and argue that progress here can bring us closer to the goal of reliable and interpretable artificial intelligence. The key themes in this work are to formulate statistical models as programs in a high-level language and learning as automatic program discovery. The fundamental technical challenge with program synthesis, however, is that it is a hard combinatorial problem. I will describe a few recent efforts that approach this challenge using a mix of ideas from formal methods and deep learning.
BIO:
Swarat Chaudhuri is an associate professor of Computer Science at Rice University. His work has two thrusts: algorithms, based on automated deduction, search, optimization, and statistical machine learning, for program analysis and synthesis; and the use of these algorithms in practical systems that make programs more reliable, more performant, and easier to write.
Swarat received a bachelor’s degree in computer science from the Indian Institute of Technology, Kharagpur, in 2001 and a doctoral degree in computer science from the University of Pennsylvania in 2007. From 2008-2011, he was an assistant professor at Pennsylvania State University. He is a recipient of the National Science Foundation CAREER award, the ACM SIGPLAN John Reynolds Doctoral Dissertation Award, the Morris and Dorothy Rubinoff Dissertation Award, a Google Research Award, and a SIGSOFT Best Paper award. He has served on program committees of many conferences in Formal Methods and Programming Languages, and chaired the 2016 Conference on Computer-Aided Verification (CAV).
Join us in the second floor atrium for a TGIF Reception at 3 p.m.!
