We use deep learning models to predict ratings of the warmth, competence, and morality of people introducing themselves in short videos. By showing which multimodal features drive these predictions, we provide insight into first impression formation. Explaining such models and their predictions is important both for training workers and for evaluating computer-based assessments of candidates.

This tutorial will explain how causal inference can help reveal cause-and-effect relationships between variables or events, and explore its applications in technology, health sciences, and the social sciences. Slides here.

Science often involves forecasting future behavior based on past observations, but this can be very challenging when you have limited observations of a system. We will discuss methods for augmenting limited datasets with theoretical models to improve forecasting success. Slides here. Seeking paid undergrad RA! Contact Emerson for details.

What is machine learning, how is it used, what does it do well, and where does it go wrong?

How/when should the (cognitive) modeler use simulation? Special attention will be paid to parameter/model recovery simulations. Slides and a Google colab notebook.