论文标题
增量在线学习算法的手势和视觉智能传感器比较
Incremental Online Learning Algorithms Comparison for Gesture and Visual Smart Sensors
论文作者
论文摘要
物联网系统中的微型机器学习（Tinyml）利用MCU作为数据处理的边缘设备。但是，传统的Tinyml方法只能执行推理，仅限于静态环境或类。真实情况通常在动态环境中起作用，从而将原始神经模型不再适合的上下文逐渐消失。因此，预先训练的模型降低了其一生中的准确性和可靠性，因为记录的数据缓慢变为过时或出现新模式。连续学习策略通过对参数进行运行时进行微调维护模型。本文比较了两个实际应用中的四种最先进的算法：i）基于加速度计数据的手势识别和ii）图像分类。我们的结果证实了这些系统的可靠性以及将它们部署到微小的MCUS中的可行性，相对于无约束计算平台的原始模型的精确度下降了几个百分点。
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.
