Behavioral Data Science II

Catalog description

Introduces students from across the behavioral sciences to foundational concepts and techniques for supervised and unsupervised machine learning. Emphasizes how these analytic methods can be used to understand cognitive, behavioral and social processes. Students build foundational understanding of machine learning basics like probability and key mathematical concepts like functions and vectors. However, these details take a backseat to applications; emphasizes a hands-on, project-centric approach where learners grapple with real-world datasets, many of which are of particular relevance to the cognitive and behavioral scientist. As they learn about specific machine learning techniques, students tackle projects across diverse domains such as forecasting relationship outcomes with tabular data, detecting 'toxic' behavior in online interactions with natural language processing (NLP) techniques, building a lie detecting model leveraging multimodal data, and image classification with neural networks. These projects instill both technical prowess and a nuanced understanding of cognition and human behavior. Equips students with a unique blend of technical and theoretical knowledge, ready to tackle complex problems at the intersection of data, mind and behavior.