Special SCS Lecture
Rashid Auditorium 4401 - Gates Hillman Centers
ALEKSANDER MADRY , NBX Career Development Associate Professor of Computer Science
Are All Features Created Equal?
Our machine learning models have attained impressive accuracy on many benchmark tasks. Yet, these models remain remarkably brittle---small perturbations of natural inputs can completely degrade their performance.
Why is this the case?
In this talk, we show that this brittleness can, in part, be attributed to the fact that our models often make decisions in a very different way than humans do. Viewing neural networks as feature extractors, we study how features extracted by neural networks may diverge from those used by humans, and how adversarially robust models seems to make progress towards bridging this gap.
Aleksander Mądry is an NBX Career Development Associate Professor of Computer Science in the MIT EECS Department, a member of CSAIL and of the Theory of Computation group. He received his Ph.D. from MIT in 2011. Prior to joining the MIT's faculty, hespent a year as a postdoctoral researcher at Microsoft Research New England and was then on the faculty of EPFL until early 2015. His research aims to identify and tackle key algorithmic challenges in today's computing. His goal is to develop theoretical ideas and tools that, ultimately, will change the way we approach optimization - in all shapes and forms, both in theory and in practice. Alexsander is also interested in understanding machine learning from a security/robustness perspective and building the science of modern ML.
Faculty Hosts: Gary Miller, Zico Kolter
For More Information: