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

TL;DR

This paper introduces the FH-RL neural mechanism that enables internal recurrence and reflective processing in neural networks, demonstrating how balanced feedback leads to stable, thought-like internal dynamics.

Contribution

It presents the FH-RL model integrating fast-weight memory, homeostasis, and reentrant feedback, with experimental analysis of its internal dynamics and stability.

Findings

Reentry gain $b3$ increases reentry quantity proportionally.

Stable reflective band emerges at moderate reentry gains.

Internal feedback becomes more structured and spectrally stable at optimal feedback levels.

Abstract

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 $\gamma$ 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~$\gamma$, while the learned feedback matrix $W_r$ remains bounded and becomes more structured at moderate gains. Critically, a stable reflective band emerges around $\gamma \approx 0.10-0.20$, 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.