ECE Seminar - Human-centered machine intelligence: From robust signal analytics to trustworthy human-technology partnership
Thu, Feb 17, 2022 @ 10:00 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Theodora Chaspari, Assistant Professor, Computer Science & Engineering Department, Texas A&M University
Talk Title: Human-centered machine intelligence: From robust signal analytics to trustworthy human-technology partnership
Abstract: Recent converging advances in sensing and computing allow the ambulatory long-term tracking of individuals yielding a rich set of real-life multimodal bio-behavioral signals, such as speech, physiology, and facial expressions. While such measurements coupled with artificial intelligence (AI) and machine learning (ML) algorithms have been heralded as promising solutions to addressing pressing societal challenges, public and expert determination of whether this integration is a good prospect is widely debated. At the same time, interactions between humans and AI are increasingly moving away from simple diagnosis of human outcomes to collaborative relationships, in which humans work side-by-side with AI systems for carrying out a set of common goals. This talk will describe new signal analytics and ML algorithms for trustworthy human-centered machine intelligence focusing on four main pillars of trustworthiness, namely robustness, privacy preservation, explainability, and fairness. We will first present our work on personalized ML models of human outcomes, generalizable learning of human states via the formulation of weakly supervised learning algorithms, and context-aware signal representations for reliably modeling interpersonal interaction. Following that, we will discuss a privacy-preserving mood recognition framework through user anonymization and examine factors of socio-demographic bias in signals and ML systems that may perpetuate social disparities in human-centered analytics. Finally, we will present our recent work on human-AI collaboration that examines how human stakeholders (e.g., clinicians) interact with AI/ML along dimensions of trust formation, maintenance, and repair. We will demonstrate the effectiveness of the proposed approaches through examples in mental health, public health, workforce training and re-skilling, and team science.
Biography: Theodora Chaspari is an Assistant Professor in the Computer Science & Engineering Department at Texas A&M University. She has received her Bachelor of Science (2010) in Electrical & Computer Engineering from the National Technical University of Athens, Greece and her Master of Science (2012) and Ph.D. (2017) in Electrical Engineering from the University of Southern California. Between 2010 and 2017 she worked as a Research Assistant at the Signal Analysis and Interpretation Laboratory at USC. She has also been a Lab Associate Intern at Disney Research (2015). Theodora's research interests lie in the areas of signal processing, machine learning, data science, and affective computing. She is a recipient of the NSF CAREER Award (2021), TAMU Montague Teaching Award (2021), USC Women in Science and Engineering Merit Fellowship (2015), and USC Annenberg Graduate Fellowship (2010). Papers co-authored with her students have been nominated and won awards at the ASC 2021, ACM BuildSys 2019, IEEE ACII 2019, ASCE i3CE 2019, and IEEE BSN 2018 conferences. She is serving as an Editor of the Elsevier Computer Speech & Language, and in various conference organization committees (ACM ICMI 2023/2020/2018, ACM IUI 2021, ACM KDD 2022, IEEE ACII 2022/2021/2019/2017, IEEE BSN 2018). She has further developed and taught several graduate and undergraduate courses in signal analytics and ML. Her work is supported by federal and private funding sources, including the NSF, NIH, NASA, IARPA, AFRL, AFOSR, General Motors, Keck Foundation, and the Engineering Information Foundation.
Host: Dr. Justin Haldar, firstname.lastname@example.org
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher