An Introduction to Causal Machine Learning - Sharif University of Tehran - Fariborz Sadeghi

Causal Machine Learning ( Causal ML ) is an umbrella term for machine learning methods that formalize the data-generation process as a structural causal model (SCM).Causal learning and reasoning is a fundamental aspect of human decision making and practical applications in AI and engineering. The concept of causality, the relationship between a cause and its effect, is a crucial idea in these fields and has been studied extensively in the last few decades.

Today's Machine Learning algorithms are missing a core attribute of human intelligence, understanding causal relations. We are born with cause-and-effect instincts, experimenting with the world causally even as infants. This capability is a necessary ingredient in ML algorithms for human-level reasoning.

Human causal learning and reasoning are closely related to counterfactual reasoning, and both require the ability to imagine hypothetical situations and analyze potential changes.
Overall, causal learning and reasoning are crucial concepts that have major applications in various fields. Understanding the theoretical foundations, perspectives, and methods of causal reasoning is essential for building more intelligent and effective systems.

This talk was presented at the Computer Science department at Sharif University of Tehran.

Видео An Introduction to Causal Machine Learning - Sharif University of Tehran - Fariborz Sadeghi канала Fariborz Sadeghi