arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.11221eess.SP
收藏

脑机接口多光谱黎曼分类的混合精度量化与并行实现

Mixed-Precision Quantization and Parallel Implementation of Multispectral Riemannian Classification for Brain--Machine Interfaces

Xiaying Wang, Tibor Schneider, Michael Hersche, Lukas Cavigelli, Luca Benini

摘要:

有了运动想象(MI)脑机接口(BMIs),我们可以仅仅通过思考执行运动动作来控制机器。实际用例需要一种可穿戴解决方案,其中使用嵌入在节能微控制器单元(MCU)上的机器学习模型在传感器附近本地完成大脑信号的分类,以确保隐私,用户舒适度和长期使用。在这项工作中,我们为嵌入式BMI解决方案的精度-成本权衡提供了实用的见解。我们提出的多光谱黎曼分类器在4类MI任务上达到75.1%的准确率。我们通过将其量化为混合精度表示来进一步缩小模型,最小精度损失为1%,这仍然比最先进的嵌入式卷积神经网络准确3.2%。我们在一个低功耗的MCU上实现了该模型,并行处理单元仅需33.39ms,每个分类消耗1.304mJ。

英文摘要:

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 33.39ms and consuming 1.304mJ per classification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑