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

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.