This course will discuss how we can enable humans and machine learning systems to interact and collaborate for more effective and accurate decision making. Topics include, but are not limited to, expert systems, recommender systems, active learning, crowdsourcing, learning with rationales, interactive machine learning, and transparency. Students are expected to delve deep into the assumptions, mathematical formulations, and algorithmic optimizations of various machine learning algorithms, read several academic papers, analyze numerous datasets, inspect implicit and explicit biases present in the analytical processes, and build an interactive and transparent machine learning system.
[(CS 422 with min. grade of C and CS 430 with min. grade of C)]