English

Self-Organizing Language

Computation and Language 2025-11-18 v2 Artificial Intelligence Machine Learning Neurons and Cognition

Abstract

We introduce a novel paradigm of emergent local memory. It is a continuous-learning completely-parallel content-addressable memory encoding global order. It demonstrates how local constraints on uncoordinated learning can produce topologically protected memories realizing emergent symbolic order. It is therefore a neuro-symbolic bridge. It further has the ability to produce human language without data, by exploiting its own self-organizing dynamics. It teaches us that words arise as a side-effect of emergent symbolic order, and that human language patterns at all structural levels reflect a universal mechanism of word formation (which is subregular). This work answers essential questions about the existence \& origin of all the human language data.

Keywords

Cite

@article{arxiv.2506.23293,
  title  = {Self-Organizing Language},
  author = {P. Myles Eugenio and Anthony Beavers},
  journal= {arXiv preprint arXiv:2506.23293},
  year   = {2025}
}

Comments

27 pages, 14 figures; Name changed from "Objective-Free Local Learning and Emergent Language Structure in Thinking Machines"

R2 v1 2026-07-01T03:38:34.795Z