Interpretability and Implicit Model Semantics in Biomedicine and Deep Learning

/in /by

Publication Date: 3/23/2026

Event: Nature Machine Intelligence

Reference: pp. 1-4, 2026

Authors: Jonathan Warrell, NEC Laboratories America, Inc.; Michael Gancz, Yale University; Hussein Mohsen, Yale University; Prashant Emani, Yale University; Mark Gerstein, Yale University

Abstract: 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 model’s semantics and illustrate our framework with examples from biomedicine.

Publication Link: https://rdcu.be/e9uYh