Lazy Learning

Abstract

Dr. Shonn Cheng recently conducted an R U Serious session for META Lab members via Teams, focusing on lazy learning in machine learning. This session introduced the concept of lazy learning algorithms, which defer generalization until a query is made, contrasting them with eager learning approaches. Participants explored key lazy learning models, such as k-Nearest Neighbors (k-NN), and discussed their advantages, limitations, and applications in various research contexts. Dr. Cheng provided hands-on demonstrations in R, guiding participants through implementing lazy learning algorithms, tuning hyperparameters, and evaluating model performance. The session emphasized the importance of selecting appropriate models based on data characteristics and research objectives, equipping participants with practical insights for applying lazy learning methods in their work.

Shonn Cheng

Assistant Professor

My research interests include applying a variety of analytical methods to study motivation, expertise, and technology-enhanced training.