2018 Hellman Fellow
Assistant Professor, Engineering
Project Title: Weakly supervised machine learning with constraints and prior knowledge
Project Description: Humans are often able to learn from high level instructions for how a task should be performed, or what it will look like when completed. In this project, Ermon’s team will explore whether a similar principle can be applied to teaching machines; can we supervise machine learning systems without individual examples by instead describing the structure of desired outputs?