Dialectics for Artificial Intelligence
Entropy · 29.05.2026 · 28 (6) · 611
DOI: 10.3390/e28060611 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 29.05.2026. Verfasst von Zhengmian Hu. Beteiligte Einrichtung: Adobe Research, Adobe Inc., 345 Park Avenue, San Jose, CA 95110-2704, USA. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Can artificial intelligence discover, from raw experience and without human supervision, concepts that humans have discovered? One challenge is that human concepts themselves are fluid: conceptual boundaries can shift, split, and merge as inquiry progresses (e.g., Pluto is no longer considered a planet). To make progress, we need a definition of “concept” that is not merely a dictionary label, but a structure that can be revised, compared, and aligned across agents. We propose an algorithmic information viewpoint that treats a concept as an information object defined only through its structural relation to an agent’s total experience. The core constraint is determination: a set of parts forms a reversible consistency relation if any missing part is recoverable from the others (up to the standard logarithmic slack in Kolmogorov complexity). This reversibility prevents “concepts” from floating free of experience and turns concept existence into a checkable structural claim. To judge whether a decomposition is natural, we define excess information, measuring the redundancy overhead introduced by splitting experience into multiple separately described parts. On top of these definitions, we formulate dialectics as an optimization dynamics: as new patches of information appear (or become contested), competing concepts bid to explain them via shorter conditional descriptions, driving systematic expansion, contraction, splitting, and merging. Finally, we formalize low-cost concept transmission and multi-agent alignment using small grounds that allow another agent to reconstruct the same concept under a shared protocol, making communication a concrete compute-bits trade-off.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Adobe Research, Adobe Inc., 345 Park Avenue, San Jose, CA 95110-2704, USA.
ORCID-Profile: Zhengmian Hu
Zitieren
APA
Hu, Z. (2026). Dialectics for Artificial Intelligence. Entropy, 28(6), 611. https://doi.org/10.3390/e28060611
Vancouver
Hu Z. Dialectics for Artificial Intelligence. Entropy. 2026;28(6):611. doi:10.3390/e28060611
BibTeX
@article{Hu2026,
author = {Hu, Zhengmian},
title = {Dialectics for Artificial Intelligence},
journal = {Entropy},
year = {2026},
volume = {28},
number = {6},
pages = {611},
doi = {10.3390/e28060611}
}
EUVIMED