2026/01/31 by I. K. Kominis, C. Xie, S. Li +2 · 1 citation
Computer Science · Physics and Astronomy · #cs.LG #physics.bio-ph #quant-ph
paper · pdf · doi:10.48550/arxiv.2601.10588
published as New J. Phys. 28, 074511 (2026) · 11 pages, 4 figures
arxiv created 2026/08/03 · arxiv updated 2026/08/04
Whether neural information processing is entirely classical or involves quantum-mechanical elements remains an open question. Here we propose a model-agnostic, information-theoretic test of nonclassicality that bypasses microscopic assumptions and instead probes the structure of neural representations themselves. Using autoencoders as a transparent model system, we introduce a Bell-type consistency test in latent space, and ask whether decoding statistics obtained under multiple readout contexts can be jointly explained by a single positive latent-variable distribution. By shifting the search for quantum-like signatures in neural systems from microscopic dynamics to experimentally testable constraints on information processing, this work opens a new route for probing the fundamental physics of neural computation. The proposed test identifies violations of classical latent-variable consistency at the level of statistical representations, without assuming a specific underlying physical mechanism.