How can machine learning assist with program analysis? What can we learn from millions of lines of code? Combining the world of formal analysis with learned statistical models has been yielding increasingly useful results. In this talk, I will give a brief overview of the area and some recent work, and discuss the research and practical challenges in this interdisciplinary area.
Wed 23 Oct Times are displayed in time zone: Beirut change
|16:00 - 16:45|
|Machine Learning for Program Analysis|
Miltiadis AllamanisMicrosoft Research, Cambridge
|16:45 - 17:30|
|An Open Source Hardware-Software Blueprint for Flexible Deep Learning Specialization|
Thierry MoreauUniversity of Washington