“Machine Learning for Human Learning”
Monday, March 19, 11:45 AM
Human learning, both in the standard classroom setting and in other settings, e.g., online learning, is crucial to advancing human intelligence. Personalized learning, i.e., recommending personalized remediation or enrichment activities to each learner based on their individual background, interests, and learning progress, has the potential to significantly improve human learning.
In this talk, I will present a series of machine learning (ML) methods towards the goal of delivering personalized learning experiences at large scale. First, I will discuss a series of novel interpretable learner-response models that characterize the complex relationship between assessment questions and underlying concepts; these models give us an intuitive understanding of the knowledge state of each learner. Then, I will discuss a novel linear estimator that provides an exact and nonasymptotic analysis of the estimation error in learner and content parameters; this error analysis is more accurate than common asymptotic analyses for realistic problem sizes, thus improving the reliability of personalization.
Andrew S. Lan is a postdoctoral research associate in the EDGE lab at the Department of Electrical Engineering at Princeton University. His research interests are in the development of ML methods for educational applications including learning and content analytics, personalized learning action selection, automated grading and feedback, and social learning. His work has resulted in over 20 publications in top conferences and journals in machine learning and educational data mining. His algorithms for personalized learning are integrated into OpenStax Tutor, the commercial-grade personalized learning platform of OpenStax; In the current academic year, nearly 1.5 million U.S. college students are using OpenStax’s collection of 29 free, online textbooks. He has also organized a series of workshops on machine learning for education; see http://ml4ed.cc for details. He received his B.S. degree in physics and mathematics from the Hong Kong University of Science and Technology, and his M.S.and Ph.D. degrees in electrical engineering from Rice University in 2014 and 2016, respectively.