Hi folks,
We have a HCI group meeting this Tuesday (July 24th) at 11:45 @DGP Seminar room. In this meeting, Joseph Jay Williams, a new faculty member of CS dept. who has been working on CS Education and HCI, will be presenting on his research approach o and some past projects on crowdsourced, dynamic personalized A/B testing using reinforcement learning and discuss some ongoing/future work. He is interested in seeing who might like to collaborate on these kinds of projects, now or in the future. or to apply the methodologies for dynamic A/B testing or reinforcement learning to their ongoing projects.
The information for the meeting and the place to add questions or comments linked to here https://docs.google.com/document/d/147QhhyTPVFJ1inKiJpWt60nyYarAVQluVqAHBD5pRyk/edit?usp=sharing. Feel free to make comments and add questions in the document, as well as provide relevant links. Details are also attached below.
Thanks, Seyong —— Adapting User Technologies: Bridging Designers, Machine Learning and Psychology through Collaborative, Dynamic, Personalized Experimentation
Enhancing people's real-world learning and thinking is a challenge for HCI and psychology, while AI aims to build systems that can behave intelligently in the real-world. This talk presents a framework for redesigning the everyday websites people interact with to function as: (1) Intelligent adaptive agents that implement machine learning algorithms to dynamically discover how to optimize and personalize people’s learning and reasoning. (2) Micro-laboratories for psychological experimentation and data collection.
I present an example of how this framework is used to create “MOOClets” that embed randomized experiments into real-world online educational contexts – like learning to solve math problems. Explanations (and experimental conditions) are crowdsourced from learners, teachers and scientists. Dynamically changing randomized experiments compare the learning benefits of these explanations in vivo with users, continually adding new conditions as new explanations are contributed.
Algorithms (for multi-armed bandits, reinforcement learning, Bayesian Optimization) are used for real-time analysis (of the effect of explanations on users’ learning) and optimizing policies that provide the explanations that are best for different learners. The framework enables a broad range of algorithms to discover how to optimize and personalize users’ behavior, and dynamically adapt technology components to trade off experimentation (exploration) with helping users (exploitation). ——
------------------------------------------ Dynamic Graphics Project Lab., Department of Computer Science, University of Toronto, Seyong Ha