Special CNS Seminar

Title: AI and Emotion-Aware Systems

Abstract:  Emotions influence memory, decision-making and well-being.  In order to advance the fundamental understanding of human behavior and emotions and build smarter affective technology we need to perform research in-situ. It is now possible to quantify behaviors and emotional responses on a large scale using ubiquitous sensors (e.g., webcams and microphones) in everyday environments.  I will present novel machine learning methods for physiological and behavioral measurement that allow for passive non-contact tracking of emotions via these devices. This will include highly scalable measurement of facial expressions, cardio-pulmonary signals and sympathetic nervous system activity.  I will follow this with insights from analysis of some of the world's largest datasets of naturalistic human behavior (featuring examples from millions of individuals) and show how this data has allowed us to corroborate and extend the understanding of people, social norms and culture. Finally, I will show examples of new Human-Computer interfaces that leverage behavioral and physiological signals, including emotion-aware natural language conversation and VR/AR systems.