Abstract
You have designed experiments and collected a lot of data that may reveal certain attributes of interest. Now you ask: How many basic patterns are there? What are typical patterns, and what are outliers? How to connect them to your attributes of interest? What if you don’t know what you are looking for? I will present a series of work in computer vision as well as applications that involve unsupervised learning of visual concepts, unsupervised instance selection, unsupervised learning of data-driven prototypicality, and predictive learning cross data modalities.
Short Bio
Stella Yu received her Ph.D. from Carnegie Mellon University, where she studied robotics at the Robotics Institute and vision science at the Center for the Neural Basis of Cognition. Before she joined the University of Michigan faculty in Fall 2022, she has been the Director of Vision Group at the International Computer Science Institute, a Senior Fellow at the Berkeley Institute for Data Science, and on the faculty of Computer Science, Vision Science, Cognitive and Brain Sciences at UC Berkeley. Dr. Yu is interested not only in understanding visual perception from multiple perspectives, but also in using computer vision and machine learning to automate and exceed human expertise in practical applications.