# Causal Learning **Domain:** Artificial Intelligence / Machine Learning / World Models **Doc Type:** Concept Node **Maturity:** Developed **Related:** [[Machine Learning]], [[Inference]], [[World Modeling]], [[Leela AI]] --- ## Definition **Causal learning** is the attempt to learn how events, actions or variables produce changes rather than merely discovering statistical association. A causal model can support explanation, intervention and counterfactual reasoning: what is likely to happen if an action changes? ## Corpus Function Causal learning matters to [[Leela AI]] because process intelligence must distinguish co-occurrence from operational sequence. It also interfaces with [[World Modeling]] and [[Inference]] throughout the machine-intelligence ontology. ## Evidence Boundary A system’s use of causal models does not prove general intelligence or conscious understanding. It establishes a stronger relationship to intervention and explanation than pattern correlation alone. ## Key Insight **Prediction asks what comes next; causal learning asks what difference an action makes.** ## Simple Reminders, Quotations, and Thoughts > "The effort to build machines that can think is certain to make us aware of aspects of thought that are not yet fully understood." > **— Mary Catherine Bateson**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Machine Succession/Building Thinking Machines Reveals Thought Itself by Mary Catherine Bateson|Building Thinking Machines Reveals Thought Itself by Mary Catherine Bateson]] > "But our limitations in terms of generating new knowledge are as much about asking the right questions as they are about more efficiently solving established and well-framed puzzles." > **— Sarah Demers**, *2015, Edge annual question “What Do You Think About Machines That Think?”* [[reminders/Information/Knowledge Depends on Asking Better Questions by Sarah Demers|Knowledge Depends on Asking Better Questions by Sarah Demers]]