By Abhishek Chakraborty (Lawrence University)
Information
We have developed several web-based, interactive apps to aid in the instruction of specific Machine Learning concepts and help students in their understanding of these ideas. We are interested in presenting these apps live during the Poster & Beyond session and soliciting feedback from colleagues. We are currently class-testing these apps (in introductory machine learning courses at small liberal arts colleges with 15-30 students per class) and hope to present preliminary results (student and instructor feedback, if applicable) during the session as well. These apps are intended to improve student understanding of the bias-variance trade-off and differences between different classification metrics (e.g. accuracy vs. sensitivity). They are designed for students from all backgrounds since they visually explore concepts without requiring any mathematical calculations.
We are in the initial stages of testing the apps. This consists of having students fill out surveys regarding the design and usefulness of our apps. In addition, we have contacted several faculty at other institutions to class-test the apps. In addition to collecting survey data from those students, we will be collecting survey data from instructors on how useful they found the apps to be. Based on the results of these surveys we intend to modify the apps and conduct a larger study in the future.