My research has two complementary threads: (1) human optimization, which involves the development of software tools to improve how people learn, remember, and make decisions, and (2) cognitively informed machine learning, which involves the development of machine learning algorithms that leverage insights from human perception and cognition. These two threads often inform one another via computer simulation models of human cognition that allow us to characterize and predict behavior. Using these models, one can determine the most effective means of teaching and the manner in which to best present information for human consumption. I'm just starting a project to instrument smart digital textbooks to boost student learning. Models of cognition can also suggest new architectures for building intelligent machines.
human optimization, cognitively informed machine learning, computational models of human cognition, applications of machine learning to problems in engineering, developing tools and techniques that improve human learning, retention, performance
CSCI 4950 - Senior Thesis
Spring 2018 / Spring 2020 / Fall 2020
Provides an opportunity for senior computer science majors to conduct exploratory research in computer science. Department enforced restriction, successful completion of a minimum of 36 credit hours of Computer Science coursework and approved WRTG. May be repeated up to 8 total credit hours.
CSCI 5822 - Probabilistic Models of Human and Machine Learning
Introduces a set of modeling techniques that have become a mainstay of modern artificial intelligence, cognitive science and machine learning research. These models provide essential tools for interpreting the statistical structure of large data sets and for explaining how intelligent agents analyze the vast amount of experience that accumulates through interactions with an unfamiliar environment. Recommended prerequisite: undergraduate course in probability and statistics.