no. 16 · Tuesday 17 November 2026
Online Neural Network Training via Closed-Loop Model-Free Tracking Control: An Empirical Study
Abstract
Training artificial neural networks predominantly relies on offline, gradient-based backpropagation algorithms. In contrast, biological circuits process and retain information through decentralized, continuous-time adaptation. In this work, we explore an online, gradient-free learning methodology by formulating the tuning of synaptic weights as a closed-loop trajectory tracking problem driven by model-free control principles. Rather than performing global optimization across static parameters, decentralized controllers adjust synaptic interactions in real-time using solely local input-output tracking errors. We present an exploratory benchmark neural architecture, whose purpose is to assess the dynamic resilience of the proposed approach, particularly in tracking target outputs and adapting to abrupt non-stationarities and structural perturbations (such as topological changes or dynamic dropout) without requiring offline retraining. This empirical preliminary study provides a proof-of-concept for control-theoretic learning paradigms and outlines the foundation for scalable, dynamically evolving connectome frameworks.
- comments
- 13 pages, 6 figures, Submitted to the 9th Annual Learning for Dynamics & Control Conference
- fields
- Optimization and Control