Objective-Free Local Learning and Emergent Language Structure in Thinking Machines

• URL: http://arxiv.org/abs/2506.23293v1
• Date: Sun, 29 Jun 2025 15:29:13 GMT
• Title: Objective-Free Local Learning and Emergent Language Structure in Thinking Machines
• Authors: P. Myles Eugenio,
• Abstract summary: We present a neuro-symbolic framework for generative language modeling based on local, event-driven emergent learning.<n>At its core is a hierarchical Hopfield memory chain acting as a compositional short-term memory and dynamic tokenizer.<n>We demonstrate that briefly activating a new neuron during inference binds distributed multi-scale token features into a symbolic embedding.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a neuro-symbolic framework for generative language modeling based on local, event-driven emergent learning. At its core is a hierarchical Hopfield memory chain acting as a compositional short-term memory and dynamic tokenizer (retokenizer). Rather than relying on predefined tokens or supervision, the model builds structure from scratch, learning symbol sequences as multi-scale representations. It constructs projection tensors that bind co-occurring features into hierarchical tokens, introducing redundancy (i.e an emergent gauge structure) and enabling compression of local activations into long-range dependencies. Curiously, we find that the retokenizer can filter natural language patterns from noise, generating synthetic languages with coherent internal morphology -- quantifiably the same as human language. Language is learned in a local (Hebbian) fashion, where model constraints dictate allowed emergent structure, and new information is retained in alignment with this structure. The absence of a global objective enables a form of plasticity not found in conventional language models, allowing the system to generalize beyond its initial inference class -- even without explicit data. We demonstrate that briefly activating a new neuron during inference binds distributed multi-scale token features into a symbolic embedding. These emergent embedding neurons act as long-term memory and support a key-value mechanism for compositional inference and generalization. This architecture provides a methodological foundation for studying how symbolic structure can emerge from local neural learning. It offers a new pathway for building scalable, interpretable neuro-symbolic systems -- where tokens, grammar, and reasoning arise as compressed memory traces within a Hopfield hierarchy. This approach advances the development of neuromorphic architectures for generative language models.

Related papers

• Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures [49.19753720526998]
  We derive theoretical scaling laws for neural network performance on synthetic datasets.<n>We validate that convolutional networks, whose structure aligns with that of the generative process through locality and weight sharing, enjoy a faster scaling of performance.<n>This finding clarifies the architectural biases underlying neural scaling laws and highlights how representation learning is shaped by the interaction between model architecture and the statistical properties of data.
  arXiv  Detail & Related papers  (2025-05-11T17:44:14Z)
• Hebbian learning the local structure of language [0.0]
  We derive the foundations of an effective human language model inspired by microscopic constraints.<n>It has two parts: (1) a hierarchy of neurons which learns to tokenize words from text (whichiswhatyoudowhenyoureadthis); and (2) additional neurons which bind the learned symanticless patterns of the tokenizer into a symanticful token.
  arXiv  Detail & Related papers  (2025-03-03T21:15:57Z)
• LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning [73.98142349171552]
  LOGICSEG is a holistic visual semantic that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge. During fuzzy logic-based continuous relaxation, logical formulae are grounded onto data and neural computational graphs, hence enabling logic-induced network training. These designs together make LOGICSEG a general and compact neural-logic machine that is readily integrated into existing segmentation models.
  arXiv  Detail & Related papers  (2023-09-24T05:43:19Z)
• A Recursive Bateson-Inspired Model for the Generation of Semantic Formal Concepts from Spatial Sensory Data [77.34726150561087]
  This paper presents a new symbolic-only method for the generation of hierarchical concept structures from complex sensory data. The approach is based on Bateson's notion of difference as the key to the genesis of an idea or a concept. The model is able to produce fairly rich yet human-readable conceptual representations without training.
  arXiv  Detail & Related papers  (2023-07-16T15:59:13Z)
• Physics of Language Models: Part 1, Learning Hierarchical Language Structures [51.68385617116854]
  Transformer-based language models are effective but complex, and understanding their inner workings and reasoning mechanisms is a significant challenge.<n>We introduce a family of synthetic CFGs that produce hierarchical rules, capable of generating lengthy sentences.<n>We demonstrate that generative models like GPT can accurately learn and reason over CFG-defined hierarchies and generate sentences based on it.
  arXiv  Detail & Related papers  (2023-05-23T04:28:16Z)
• ROSE: A Neurocomputational Architecture for Syntax [0.0]
  This article proposes a neurocomputational architecture for syntax, termed the ROSE model. Under ROSE, the basic data structures of syntax are atomic features, types of mental representations (R), and are coded at the single-unit and ensemble level. Distinct forms of low frequency coupling and phase-amplitude coupling (delta-theta coupling via pSTS-IFG; theta-gamma coupling via IFG to conceptual hubs) then encode these structures onto distinct workspaces (E)
  arXiv  Detail & Related papers  (2023-03-15T18:44:37Z)
• Dynamic Inference with Neural Interpreters [72.90231306252007]
  We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules. inputs to the model are routed through a sequence of functions in a way that is end-to-end learned. We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
  arXiv  Detail & Related papers  (2021-10-12T23:22:45Z)
• Low-Dimensional Structure in the Space of Language Representations is Reflected in Brain Responses [62.197912623223964]
  We show a low-dimensional structure where language models and translation models smoothly interpolate between word embeddings, syntactic and semantic tasks, and future word embeddings. We find that this representation embedding can predict how well each individual feature space maps to human brain responses to natural language stimuli recorded using fMRI. This suggests that the embedding captures some part of the brain's natural language representation structure.
  arXiv  Detail & Related papers  (2021-06-09T22:59:12Z)
• The Unstoppable Rise of Computational Linguistics in Deep Learning [17.572024590374305]
  We trace the history of neural networks applied to natural language understanding tasks. We argue that Transformer is not a sequence model but an induced-structure model.
  arXiv  Detail & Related papers  (2020-05-13T16:51:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.