# Neuromorphic Energy-Aware Learning for Adaptive Deep Brain Stimulation

arXiv: https://arxiv.org/abs/2606.28600 · HTML: https://mlsanity.com/paper/2606.28600/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 46 references that are in the map.
- First posted on arXiv 26 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [Neuromorphic Intermediate Representation: A Unified Instruction Set for Interoperable Brain-Inspired Computing](https://mlsanity.com/paper/2311.14641/) (2023)
- [Large-Scale Neuromorphic Spiking Array Processors: A quest to mimic the brain](https://mlsanity.com/paper/1805.08932/) (2018)
- [Sub-mW Neuromorphic SNN audio processing applications with Rockpool and Xylo](https://mlsanity.com/paper/2208.12991/) (2022)
- [Efficient Event-based Delay Learning in Spiking Neural Networks](https://mlsanity.com/paper/2501.07331/) (2025)
- [Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity](https://mlsanity.com/paper/2502.01330/) (2025)
- [Neurophysiologically Realistic Environment for Comparing Adaptive Deep Brain Stimulation Algorithms in Parkinson Disease](https://mlsanity.com/paper/2505.09624/) (2025)

## Abstract (arXiv)

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.