Closed-Loop Neural Interfaces with Embedded Machine Learning
This work addresses the problem of enabling closed-loop neural interfaces for neurological disorders, but it appears incremental as it builds on existing methods with optimizations.
The paper tackles the challenge of deploying machine learning on low-power neural devices by reviewing design trade-offs and presenting an optimized tree-based model, showing that it outperforms conventional models in applications like seizure detection and motor decoding.
Neural interfaces capable of multi-site electrical recording, on-site signal classification, and closed-loop therapy are critical for the diagnosis and treatment of neurological disorders. However, deploying machine learning algorithms on low-power neural devices is challenging, given the tight constraints on computational and memory resources for such devices. In this paper, we review the recent developments in embedding machine learning in neural interfaces, with a focus on design trade-offs and hardware efficiency. We also present our optimized tree-based model for low-power and memory-efficient classification of neural signal in brain implants. Using energy-aware learning and model compression, we show that the proposed oblique trees can outperform conventional machine learning models in applications such as seizure or tremor detection and motor decoding.