Interpretability and implicit model semantics in biomedicine and deep learning

doi:10.1038/s42256-026-01177-0

Interpretability and implicit model semantics in biomedicine and deep learning

2026-03-23

0

PRE

AI

DOI：10.1038/s42256-026-01177-0

Original

Original request for help

Save

Abstract

En 中文

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.

Keywords:

Computational models

Computer science

Engineering

general

Interpretability and implicit model semantics in biomedicine and deep learning

Abstract

Journal

Organization