Tiny machine learning (TinyML) in IoT systems exploits MCUs as edge devices for data processing. However, traditional TinyML methods can only perform inference, limited to static environments or classes. Real case scenarios usually work in dynamic environments, thus drifting the context where the original neural model is no more suitable. For this reason, pre-trained models reduce accuracy and reliability during their lifetime because the data recorded slowly becomes obsolete or new patterns appear. Continual learning strategies maintain the model up to date, with runtime fine-tuning of the parameters. This paper compares four state-of-the-art algorithms in two real applications: i) gesture recognition based on accelerometer data and ii) image classification. Our results confirm these systems' reliability and the feasibility of deploying them in tiny-memory MCUs, with a drop in the accuracy of a few percentage points with respect to the original models for unconstrained computing platforms.
翻译:在IoT系统中,小机器学习(TinyML)利用MCU作为数据处理的边缘装置,但传统的TinyML方法只能进行推论,限于静态环境或等级。真实的情景通常在动态环境中运作,从而漂移原始神经模型不再适合的环境。因此,由于所记录的数据慢慢过时或出现新的模式,经过预先培训的模型在其寿命期间降低了准确性和可靠性。持续学习战略保持了模型的更新,运行时间微调参数。本文比较了两种实际应用中的四种最先进的算法:i)基于加速计数据或图像分类的手势识别。我们的结果证实了这些系统的可靠性,以及将其用于微缩的MCUs的可行性,与未受限制的计算机平台的原始模型相比,几个百分点的精确度下降。