Shannon observables: A scalable approach to information decomposition

arXiv:2504.15779 · cs.IT, cs.AI, cs.LG, math.IT, nlin.AO, physics.data-an · Submitted 2025-04-22 · Read on arXiv

cs.IT, cs.AI, cs.LG, math.IT, nlin.AO, physics.data-an

Submitted: 2025-04-22

Updated: 2026-11-11

Comments: 28 pages, 8 figures, 3 tables. v2: substantially revised and retitled (formerly "Shannon invariants"); adds an analysis of error-correcting codes, an extension to directed information flow with a cortical atlas from MEG recordings, single-neuron lesion and dropout experiments, and bounds linking vulnerability to performance loss after neuron removal

Code: https://github.com/Priesemann-Group/nninfo

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Sources

Related papers