Thomas Icard (Stanford)

Causal Abstraction: Some Theory and a Few Applications

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.

Thomas Icard is the Clarence Irving Lewis Professor of Philosophy and Professor of Computer Science (by courtesy) at Stanford University. He works at the intersection of philosophy, cognitive science, and computer science, especially on topics related to causality, language, decision making, and reasoning. A driving theme for much of this work is the productive tension between normative and descriptive perspectives on natural and artificial intelligence.

About the Seminar Series

The last few years have seen a substantial increase in the reported success of machine learning (ML), and generative artificial intelligence (AI). These impact practices in delivering services from financial institutions to entertainment and medicine. However scientific research also increasingly relies on large data sets, whose analysis leverages ML/AI. This seminar series aims to investigate if and how the paradigm for scientific research has changed or should change to incorporate these new tools and the possibilities they open.

A diverse group of scholars engaged in scientific research, method development, and historical and epistemological investigations will give a 50-minute presentation, followed by discussion.

The event is open to all. Stanford students and postdocs have the opportunity to engage more directly with speakers and topics by enrolling in the Canvas course here.