Timezone: »

 
(Invited Talk) Percy Liang: Learning with Adversaries and Collaborators
Percy Liang

Fri Dec 08 01:50 PM -- 02:35 PM (PST) @
in Learning in the Presence of Strategic Behavior »

We argue that the standard machine learning paradigm is both too weak and too string. First, we show that current systems for image classification and reading comprehension are vulnerable to adversarial attacks, suggesting that existing learning setups are inadequate to produce systems with robust behavior. Second, we show that in an interactive learning setting where incentives are aligned, a system can learn a simple natural language from a user from scratch, suggesting that much more can be learned under a cooperative setting.

Author Information

Percy Liang (Stanford University)
Percy Liang

Percy Liang is an Assistant Professor of Computer Science at Stanford University (B.S. from MIT, 2004; Ph.D. from UC Berkeley, 2011). His research spans machine learning and natural language processing, with the goal of developing trustworthy agents that can communicate effectively with people and improve over time through interaction. Specific topics include question answering, dialogue, program induction, interactive learning, and reliable machine learning. His awards include the IJCAI Computers and Thought Award (2016), an NSF CAREER Award (2016), a Sloan Research Fellowship (2015), and a Microsoft Research Faculty Fellowship (2014).

More from the Same Authors