Learning in Machines and Brains Virtual Meeting on Causal Inference
Thursday, July 30, 2020- Friday, July 31, 2020
Meeting from 12-2 p.m. EDT
Overview
A virtual workshop on Causal Inference across Machine Learning, Economics, Philosophy and beyond, to be held via Zoom on July 30 and 31 from 12PM - 2PM EDT. This meeting will be hosted by CIFAR’s Learning in Machines & Brains (LMB) program. Our intent is to further explore causality at the intersection of several disciplines across the Academy based on our interest in understanding both the ability and limitations of current AI systems in their ability to understand the world around us. This meeting will be a first of what we hope to be an ongoing collaborative and interdisciplinary conversation that bridges disciplines and builds more robust frameworks for thinking about causal inference. The workshop will include sessions on:
- Quasiexperimental Methods of Causality
- Causality, Agency, Representations and Discovery of Causal Variables and Structure
The CIFAR LMB Program Workshop on Causal Inference is generously supported by the Alfred P. Sloan Foundation
Agenda
Thursday July 30 | |
12:00-12:10pm | Welcome & Introductions |
12:10-12:30pm | Judea Pearl Science vs. Data: Contesting the Soul of Data-Science |
12:30-1:00pm | Discussion |
1:00-1:20pm | Alison Gopnik New Work on Variable Choice and Extrapolation of Causal Relations to New Examples (both in toddlers!) |
1:20-1:50pm | Discussion |
1:50-2:00pm | Final remarks |
Friday July 31 | |
12:00-12:05pm | Welcome |
12:05-12:25pm | Yoshua Bengio Causal Discovery from Unknown Interventions |
12:25-12:40pm | Discussion |
12:40-1:00pm | Victor Chernozhukov Impact of Masks, Policies, Behavior on Early Covid-19 Pandemic in the US: an Investigation via Causal DAGs |
1:00-1:15pm | Discussion |
1:15-1:35pm | Caroline Uhler Causal Inference from Interventional Data |
1:35-1:50pm | Discussion |
1:50-2:00pm | General Discussion & closing |
About CIFAR
CIFAR is a Canadian-based global research organization that convenes extraordinary minds to address the most important questions facing science and humanity By supporting long-term interdisciplinary collaboration, CIFAR provides researchers with an unparalleled environment of trust, transparency and knowledge sharing. Our time-tested model inspires new directions of inquiry, accelerates discovery and yields breakthroughs across borders and academic disciplines.