ASSET Seminar: “Curious Embeddings, Hazy Oracles, and the Path to Safe, Cooperative AI”
December 4 at 12:00 PM - 1:15 PM
Abstract:
Cooperation through safe and trustworthy communication and interaction is fundamental to how human teams accomplish complex tasks. Yet, despite significant–and sometimes revolutionary–advances in AI, we have barely begun to unlock the potential of safe, cooperative AI. This may stem from our limited understanding of how multimodal, large-scale AI models function, the one-sided nature of contemporary, fully-supervised AI approaches, or social concerns about human-AI collaboration. In this talk, I will dive into these layers of inquiry, beginning with a principled exploration of what the embeddings in large-scale foundation models reveal about the underlying problem and data, including new results disentangling sample-size from Bayes error and decision-boundary complexity. I will then introduce the concept of the human collaborator as a “hazy oracle”–a fallible partner rather than an omniscient information source–and establish a framework for modeling human-supplied error during collaboration. Building on these foundational insights, I will conclude with applications of these ideas to foster safe and effective human-AI collaboration in the health sciences.
Zoom Link (if unable to attend in-person): https://upenn.zoom.us/j/99385572884
Jason Corso
Professor and Co-Founder/Chief Scientist of the AI startup Voxel51
Corso is Professor of Robotics, Electrical Engineering and Computer Science at the University of Michigan and Co-Founder / Chief Scientist of the AI startup Voxel51. He received his PhD at The Johns Hopkins University in 2005 in Computer Science, and was a Postdoc in Radiology, Neuroscience, and Statistics at UCLA 2006-2007. He is the recipient of a U Michigan EECS Outstanding Achievement Award 2018, Google Faculty Research Award 2015, the Army Research Office Young Investigator Award 2010, National Science Foundation CAREER award 2009, a member of the 2009 DARPA Computer Science Study Group, and a recipient of the Link Foundation Fellowship in Advanced Simulation and Training 2003. Corso has authored more than 150 peer-reviewed papers and hundreds of thousands of lines of open-source code on topics of his interest including AI, interaction, computer vision, robotics, and machine learning. He is a member of the AAAI, ACM, MAA and a senior member of the IEEE.