[2604.04171] A Model of Understanding in Deep Learning Systems

Computer Science > Artificial Intelligence arXiv:2604.04171 (cs) [Submitted on 5 Apr 2026] Title:A Model of Understanding in Deep Learning Systems Authors:David Peter Wallis Freeborn View a PDF of the paper titled A Model of Understanding in Deep Learning Systems, by David Peter Wallis Freeborn View PDF HTML (experimental) Abstract:I propose a model of systematic understanding, suitable for machine learning systems. On this account, an agent understands a property of a target system when it contains an adequate internal model that tracks real regularities, is coupled to the target by stable bridge principles, and supports reliable prediction. I argue that contemporary deep learning systems often can and do achieve such understanding. However they generally fall short of the ideal of scientific understanding: the understanding is symbolically misaligned with the target system, not explicitly reductive, and only weakly unifying. I label this the Fractured Understanding Hypothesis. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.04171 [cs.AI]   (or arXiv:2604.04171v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.04171 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: David Freeborn [view email] [v1] Sun, 5 Apr 2026 16:27:43 UTC (635 KB) Full-text links: Access Paper: View a PDF of the paper titled A Model of Understanding in Deep Learning Systems, by David Peter Wallis FreebornView PDFHTML (experi...