CLEAR-FORCE: A reservoir computing framework for closed-loop brain stimulation
- 1University of Ottawa
Abstract
Electrical stimulation of brain activity has emerged as a key therapeutic intervention for neurological diseases. The success of these approaches relies on precisely tuned stimulation parameters. A major challenge is that these parameters should ideally be adjusted in real-time based on changes in brain activity. Closed-loop controllers address this challenge by monitoring brain activity and adapting stimulation according to ongoing changes in neural dynamics. While machine learning has been helpful in this context, closed-loop controllers typically do not adapt in real-time to fluctuations in brain activity. Here, we propose a novel framework based on reservoir computing to train a closed-loop, real-time neural controller. This approach, termed CLEAR-FORCE, trains the output weights of a recurrent network based on a combination of target signals and feedback from brain activity. Two series of simulations were performed, where the controller was successful at (1) inducing neural oscillations in a population of spiking neurons and (2) suppressing pathological oscillations. This framework provides a promising avenue for the implementation of neural controllers in low-powered, real-time, and adaptive hardware that harnesses machine learning for the personalized treatment of brain disorders.
Related
- Information coding strategies in biological reservoir computing for multiclass time-series classification
- Harnessing the Intrinsic Dynamics of Biological Neural Networks for Reservoir Computing
- Learning to play with spikes: characterizing, predicting, and engineering unsupervised plasticity rules for spiking reservoir computing
- Determinants of hyperparameter robustness in connectome reservoir computing
- Closed-Loop Acoustic Stimulation of Slow Oscillations Using a Wireless EEG Headband: A Polysomnography-Validated Feasibility Study.
BibTeX
@misc{morenogris2026clearforce,
title = {{CLEAR-FORCE: A reservoir computing framework for closed-loop brain stimulation}},
author = {A. Moreno-Gris and C. Godin and J.-P. Thivierge},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.05.756709},
url = {https://www.biorxiv.org/content/10.64898/2026.10.05.756709v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - CLEAR-FORCE: A reservoir computing framework for closed-loop brain stimulation
AU - A. Moreno-Gris
AU - C. Godin
AU - J.-P. Thivierge
PY - 2026
DA - 2026/10/05
PB - bioRxiv
DO - 10.64898/2026.10.05.756709
UR - https://www.biorxiv.org/content/10.64898/2026.10.05.756709v1
AB - Electrical stimulation of brain activity has emerged as a key therapeutic intervention for neurological diseases. The success of these approaches relies on precisely tuned stimulation parameters. A major challenge is that these parameters should ideally be adjusted in real-time based on changes in brain activity. Closed-loop controllers address this challenge by monitoring brain activity and adapting stimulation according to ongoing changes in neural dynamics. While machine learning has been helpful in this context, closed-loop controllers typically do not adapt in real-time to fluctuations in brain activity. Here, we propose a novel framework based on reservoir computing to train a closed-loop, real-time neural controller. This approach, termed CLEAR-FORCE, trains the output weights of a recurrent network based on a combination of target signals and feedback from brain activity. Two series of simulations were performed, where the controller was successful at (1) inducing neural oscillations in a population of spiking neurons and (2) suppressing pathological oscillations. This framework provides a promising avenue for the implementation of neural controllers in low-powered, real-time, and adaptive hardware that harnesses machine learning for the personalized treatment of brain disorders.
ER -