Computer-Assisted Learning in the Age of Machine Learning and Big Data
Big Data and, a little less so, Machine Learning are the two concepts that Computer Science is known and revered for these days. The abundance of data collected about various aspects of human life and the rigor and maturity of the methodologies for analyzing this data come together as a promise to successfully tackle large societal issues (e.g., quality of education and improving educational outcomes) at scale.
Most of my work in one way or the other rotates around education and using data, Machine Learning, and Artificial Intelligence to improve student learning. In this talk, I will discuss a series of projects I was involved in that addressed a range of challenging and existing problems. Including, building models of student behavior and learning from unstructured data, optimal use of technology for learning Math in K-12 setting, and building models from big data in the absence of conventional Machine Learning packages.
Michael Yudelson, Carnegie Mellon University (Ph.D., University of Pittsburgh, 2010) is a Project Scientist at the Human-Computer Interaction Institute of Carnegie Mellon University. He has done extensive research on student personalization in educational systems and architectural work on adaptive support architectures and their performance testing. He also received James Chen Best Student Paper Award at User Modeling 2007 conference for part of that architectural work. His doctoral project focused on service-based adaptation for the lightweight LMS serving smart content in a context of a set of CS courses. Dr. Yudelson has spent a substantial amount of time working with large volumes of student data and building innovative models of student knowledge acquisition when collaborating with Carnegie Learning and working for them as a research scientist. He has co-authored several journal publications on the topics of cognitive models of practice and knowledge transfer. Dr. Yudelson continues active work in the area of architectures of user-adaptive systems, student modeling, and Big Data analytics.