The Interplay of Data, Models, and Theories in Machine Learning
Norelli, Maria Federica, Votsis, Ioannis and Williamson, Jon (2024) The Interplay of Data, Models, and Theories in Machine Learning. Philosophy of Science. (In Press)
Abstract
This paper discusses the role of data within scientific reasoning and as evidence for theoretical claims, arguing for the idea that data can yield theoretically grounded models and be inferred, predicted, or explained from/by such models. Contrary to Bogen and Woodward's skepticism regarding the feasibility and epistemic relevance of data-to-theory and theory-to-data inferences, we draw upon scientific artificial intelligence literature to advocate that: a) many models are routinely inferred and predicted from the data and routinely used to infer and predict data: b) such models can, at least in some contexts, play the role of theoretical device.
Actions (login required)
Edit Item |