Reflecting What AI Perceives from Human Interaction

Dr. Nina Marhamati
CS Department, Sonoma State University, Rohnert Park, CA

Cerent Engineering Science Complex, Salazar Hall 2009A
3:00 PM

Abstract – Inspired by interactive art pieces and all the excitement about AI surrounding us, we wonder what machines and AI can reflect about humans and the interactions with humans. In this talk, you will hear about an AI system that we are creating to reflect on user interaction and to demonstrate how the way the user approaches the system (machine) is perceived by AI. Different machine learning and state of the art AI methods are used to detect the user's emotional state while interacting with the system. The sensory inputs are processed, and will be fused when possible, to extract information from the interaction and improve the results. The perceived interaction results are demonstrated via animations or other visuals in two or three-dimensional settings. The final product has the potential to be integrated into virtual reality or augmented reality applications. This is an interdisciplinary project with collaborators from different backgrounds in CS, EE, and art.

Dr. Nina Marhamati is an Assistant Professor of Computer Science at Sonoma State University and, on the side, provides machine learning consulting services to the industry. She was an Artificial Intelligence Fellow at Insight Data Science and received her PhD in Computer Science from Southern Illinois University, where she was a DRA Fellow and the Outstanding Graduate Assistant in 2016. She was the recipient of the Best Dissertation Award from North American Fuzzy Information Processing Society in 2017. She is passionate for applications of artificial intelligence and machine learning that make day-to-day life easier and more fulfilling. She enjoys working on interdisciplinary projects and her areas of interest include natural language processing, machine learning & data analysis, Bayesian estimation theory, computing with words, and fuzzy logic.