Symbolic, Statistical, and Causal Representations

On July 13, 2021, Prof. Bernhard Schölkopf gives a lecture on a new approach to machine learning at I-AIDA.


In machine learning, we use data to automatically find dependencies in the world, with the goal of predicting future observations. Most machine learning methods build on statistics, but one can also try to go beyond this, assaying causal structures underlying statistical dependencies. It turns out that causality can play a central role in addressing some of the hard open problems of machine learning, due to the fact that causal models are more robust to changes that occur in real world datasets. The talk will argue that causality has some shortcomings that are complementary to those of current machine learning, and the study of causal representation learning may help unify the advantages. It will also introduce some algorithms and applications in this field.

Tuesday, 07-13-2021, 05.00 p.m. – 06.00 p.m., virtual event

More details at:

This is an event of I-AIDA – International Artificial Intelligence Doctoral Academy.