How Artificial Intelligence Leads to Knowledge Why: An Inquiry Inspired by Aristotle's Posterior Analytics
This work addresses a foundational gap in AI theory for researchers and practitioners, though it is incremental as it builds on existing causal models.
The paper tackles the lack of a formal theory for the knowledge needed to predict effects of external interventions in AI, introducing a causal systems framework inspired by Aristotle to clarify knowledge types, and argues that only 'knowledge why' enables such predictions.
Bayesian networks and causal models provide frameworks for handling queries about external interventions and counterfactuals, enabling tasks that go beyond what probability distributions alone can address. While these formalisms are often informally described as capturing causal knowledge, there is a lack of a formal theory characterizing the type of knowledge required to predict the effects of external interventions. This work introduces the theoretical framework of causal systems to clarify Aristotle's distinction between knowledge that and knowledge why within artificial intelligence. By interpreting existing artificial intelligence technologies as causal systems, it investigates the corresponding types of knowledge. Furthermore, it argues that predicting the effects of external interventions is feasible only with knowledge why, providing a more precise understanding of the knowledge necessary for such tasks.