Department of Computer Science Colloquium Series

Join the Department of Computer Science for their first colloquium series in their candidate search for the Trustworthy AI Faculty. 

Artificial intelligence is being deployed in ever more consequential settings such as healthcare and autonomous driving. Thus, we must ensure that these systems are safe and trustworthy. One near-term solution is to involve a human in the decision-making process and enable the system to ask for help in difficult or high-risk scenarios. I will present recent advances in the “learning to defer” paradigm: decision-making responsibility is allocated to either a human or model, depending on who is more likely to take the correction action. Specifically, I will present novel formulations that better model the human collaborator’s expertise and that can support multiple human decision makers. I will also describe paths for future work, including improvements to data efficiency and applications to language models.

Eric Nalisnick is an assistant professor at the University of Amsterdam. He is inter- ested in building safe and robust intelli- gent systems with a human-centered design. To accomplish this, his research develops novel machine learning tech- niques, which are often rooted in proba- bilistic modeling and computational statistics. Questions of particular interest are: how can we incorporate a human's prior knowledge?, how can we detect when the system is failing?, and how to best combine human and machine deci- sion making? He previously was a post- doctoral researcher at the University of Cambridge and a PhD student at the University of California, Irvine. Eric has also held research positions at DeepMind, Microsoft, Twitter, and Amazon. He has served as an area chair for (as well as published in) all major machine learning conferences: NeurIPS, ICML, ICLR, AIStats, and UAI. Eric has been awarded the distinctions of ELLIS scholar and NWO Veni fellow.