Agenda: April 22, 2025

10 a.m. | Introduction and Welcome Remarks

Alexis Battle, Johns Hopkins Data Science and AI Institute Interim Deputy Director

10:15 a.m. | Causal Abstraction: Some Theory and a Few Applications

Thomas Icard, Clarence Irving Lewis Professor of Philosophy and Professor of Computer Science, by courtesy, Stanford University

Abstract: The importance of explaining phenomena at the right levels of abstraction is recognized throughout the sciences. The aim of the talk will be to show that abstraction itself is a rich and fruitful target of investigation, particularly when viewed through a causal lens. To illustrate potential benefits of reifying a notion of causal abstraction, we discuss: (1) a case study in scientific framework comparison, (2) analysis of ethically significant causal concepts such as discrimination, and (3) neural network interpretability. Each draws on a shared body of theoretical work on abstraction.

11:05 a.m. | Lightning Talks

Speaker information and presentation topics coming soon

11:30 a.m. | Break

1 p.m. | Building a Trustworthy AI Implementation Process

Ivor Braden Horn, Board Member of Boston Children’s Hospital, Advisory Board of Harvard Public Health Magazine, Editorial Board of Health Affairs Scholar, and former Chief Health Equity Officer at Google

Abstract: Building with AI-enabled tools in ways that are trustworthy and aligned with the vision and values of your organization requires intentionality, process, and accountability standards, in addition to the expertise within your team and partners. How to achieve that goal is still evolving. During this presentation, I will share strategic and practical insights on how to build and implement responsible, innovative health solutions at scale in the current fast-paced health technology environment.

1:50 p.m. | Lightning Talks

Speaker information and presentation topics coming soon

2 p.m. | Understanding Human Intelligence Through Human Limitations

Tom Griffiths, Clarence Irving Lewis Professor of Philosophy and Professor of Computer Science, by courtesy, Stanford University

Abstract: As machines continue to exceed human performance in a range of tasks, it is natural to ask how we might think about human intelligence in a future populated by super intelligent machines. One way to do this to think about the unique computational problems posed by human lives, and in particular by our finite computational resources and finite lifespan. Thinking in these terms highlights two problems: making efficient use of our cognitive resources, and being able to learn from limited amounts of data. It also sets up a third problem: solving computational problems beyond the scale of any one individual. I will argue that these three problems pick out the key characteristics of human intelligence, and highlight some recent progress in understanding how human minds solve them and how machines and humans might be brought into closer alignment.

3 p.m. | Panel Discussion

Panel moderator: John Hale, Professor in the Department of Cognitive Science
Panel: Tom Griffiths, Ivor Braden Horn, and Thomas Icard

4 p.m. | Closing Remarks