Neuromorphic Energy-Aware Learning for Adaptive Deep Brain Stimulation

2026-06-26

AI Summary

This work addresses the challenge that in closed-loop neuromodulation systems, stimulator energy consumption vastly exceeds the computational power required for controller inference, rendering inference-only optimization insufficient for reducing overall system energy use. To tackle this, the authors propose an energy-aware reinforcement learning approach that explicitly incorporates stimulator energy cost into the reward function for the first time, combined with sparsity-constrained knowledge distillation to jointly optimize control policy and hardware energy efficiency. Implemented on a deep spiking Q-network, a biophysically grounded basal ganglia–thalamocortical model, and the SynSense XyloAudio 3 neuromorphic processor, the method achieves a 45.2% suppression rate of pathological alpha-beta oscillations in Parkinsonian deep brain stimulation, reduces stimulation charge by 80.0%, and operates at a mere 0.52 mW inference power—yielding a 28.1× improvement in energy efficiency over conventional edge hardware.

Abstract

Neuromorphic and edge computing research has focused on reducing the inference cost of neural network controllers, yet in physical closed-loop systems the actuator can rival or exceed an efficient controller in energy. An efficient controller is therefore necessary but not sufficient, because the actuator becomes the cost worth reducing once inference no longer dominates it. Here, we introduce energy-aware learning, an approach that incorporates actuator energy directly into the reinforcement learning reward, and demonstrate it in closed-loop deep brain stimulation (DBS) for Parkinson's disease. A deep spiking Q-network, trained in a biophysical cortico-basal ganglia-thalamic circuit model, learns to suppress pathological alpha-beta oscillations by 45.2% while reducing stimulation charge by 80.0% relative to continuous DBS. Sparsity-constrained knowledge distillation compresses the policy onto the SynSense XyloAudio 3 neuromorphic processor at 0.52 mW inference power, yielding 28.1x lower energy per inference than an equivalent artificial neural network on conventional edge hardware. By co-optimizing stimulation energy and inference efficiency, the framework addresses both major power demands in implantable neuromodulation.

Problem

• energy-aware learning
• deep brain stimulation
• neuromorphic computing
• actuator energy
• implantable neuromodulation

Innovation

• energy-aware learning
• neuromorphic computing
• deep brain stimulation
• spiking neural networks
• knowledge distillation