Failure-Resistant Intelligent Interaction for Reliable Human-AI Collaboration

Abstract

My thesis is focusing on how we can overcome the gap people have against machine learning techniques that require a well-defined application scheme and can produce wrong results. I am planning to discuss the principle of the interaction design that fills such a gap based on my past projects that have explored better interactions for applying machine learning in various fields, such as malware analysis, executive coaching, photo editing, and so on. To this aim, my thesis also shed a light on the limitations of machine learning techniques, like adversarial examples, to highlight the importance of "failure-resistant intelligent interaction."