Scientific Theories and Models are structured frameworks used to explain, predict, and analyze natural or engineered phenomena. A theory provides a well-supported explanation based on empirical evidence and established principles, while a model offers a simplified representation of a system using mathematical, computational, or conceptual forms. These tools are widely applied in physics, engineering, and data-driven research to test hypotheses, guide experiments, and interpret observations under defined assumptions and constraints.
We introduce a framework to analyse interpretability in deep learning, by drawing on a formal notion of model semantics from the philosophy of science. We argue that interpretability is only one aspect of a models semantics and illustrate our framework with examples from biomedicine.