Recursive Dynamics in Fast-Weights Homeostatic Reentry Networks: Toward Reflective Intelligence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Chae, B. G.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915608977735680
author Chae, B. G.
author_facet Chae, B. G.
contents This study introduces the Fast-Weights Homeostatic Reentry Layer (FH-RL), a neural mechanism that integrates fast-weight associative memory, homeostatic regularization, and learned reentrant feedback to approximate self-referential computation in neural networks. Unlike standard transformer architectures that operate in a purely feedforward manner during inference, FH-RL enables internal recurrence without external looping, allowing prior latent states to be dynamically re-entered into the ongoing computation stream. We conduct controlled experiments sweeping the reentry gain $γ$ and evaluate emergent internal dynamics using three novel metrics: the Information Reentry Ratio (IRR), Eigen-Spectrum Recursion Index (ESRI), and Representational Drift Periodicity (RDP). Results show that reentry quantity increases proportionally with~$γ$, while the learned feedback matrix $W_r$ remains bounded and becomes more structured at moderate gains. Critically, a stable reflective band emerges around $γ\approx 0.10-0.20$, where internal feedback is maximally expressive yet spectrally stable: IRR rises smoothly, ESRI remains near zero, and RDP exhibits consistent low-frequency cycles. These findings provide quantitative evidence that reflective, thought-like internal processing can arise from a principled balance between feedback amplification and homeostatic regulation, linking modern fast-weight architectures to theories of cortical reentry and recursive cognition.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06798
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Recursive Dynamics in Fast-Weights Homeostatic Reentry Networks: Toward Reflective Intelligence
Chae, B. G.
Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
This study introduces the Fast-Weights Homeostatic Reentry Layer (FH-RL), a neural mechanism that integrates fast-weight associative memory, homeostatic regularization, and learned reentrant feedback to approximate self-referential computation in neural networks. Unlike standard transformer architectures that operate in a purely feedforward manner during inference, FH-RL enables internal recurrence without external looping, allowing prior latent states to be dynamically re-entered into the ongoing computation stream. We conduct controlled experiments sweeping the reentry gain $γ$ and evaluate emergent internal dynamics using three novel metrics: the Information Reentry Ratio (IRR), Eigen-Spectrum Recursion Index (ESRI), and Representational Drift Periodicity (RDP). Results show that reentry quantity increases proportionally with~$γ$, while the learned feedback matrix $W_r$ remains bounded and becomes more structured at moderate gains. Critically, a stable reflective band emerges around $γ\approx 0.10-0.20$, where internal feedback is maximally expressive yet spectrally stable: IRR rises smoothly, ESRI remains near zero, and RDP exhibits consistent low-frequency cycles. These findings provide quantitative evidence that reflective, thought-like internal processing can arise from a principled balance between feedback amplification and homeostatic regulation, linking modern fast-weight architectures to theories of cortical reentry and recursive cognition.
title Recursive Dynamics in Fast-Weights Homeostatic Reentry Networks: Toward Reflective Intelligence
topic Machine Learning
Artificial Intelligence
Neural and Evolutionary Computing
url https://arxiv.org/abs/2511.06798