Mixed-Precision Quantization and Parallel Implementation of Multispectral Riemannian Classification for Brain-Machine Interfaces
Metadata only
Date
2021Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
With Motor-Imagery (MI) Brain-Machine Interfaces (BMIs) we may control machines by merely thinking of performing a motor action. Practical use cases require a wearable solution where the classification of the brain signals is done locally near the sensor using machine learning models embedded on energy-efficient microcontroller units (MCUs), for assured privacy, user comfort, and long-term usage. In this work, we provide practical insights on the accuracy-cost tradeoff for embedded BMI solutions. Our proposed Multispectral Riemannian Classifier reaches 75.1% accuracy on 4-class MI task. We further scale down the model by quantizing it to mixed-precision representations with a minimal accuracy loss of 1%, which is still 3.2% more accurate than the state-of-the- art embedded convolutional neural network. We implement the model on a low-power MCU with parallel processing units taking only 33.39 ms and consuming 1.304 mJ per classification. © 2021 IEEE Show more
Publication status
publishedExternal links
Book title
2021 IEEE International Symposium on Circuits and Systems (ISCAS)Pages / Article No.
Publisher
IEEEEvent
Subject
brain-machine interface; edge computing; parallel computing; machine learning; deep learning; motor imageryOrganisational unit
03996 - Benini, Luca / Benini, Luca
More
Show all metadata
ETH Bibliography
yes
Altmetrics