Tiny Machine Learning (TinyML) is a new frontier of machine learning. By squeezing deep learning models into billions of IoT devices and microcontrollers (MCUs), we expand the scope of AI applications and enable ubiquitous intelligence. However, TinyML is challenging due to hardware constraints: the tiny memory resource makes it difficult to hold deep learning models designed for cloud and mobile platforms. There is also limited compiler and inference engine support for bare-metal devices. Therefore, we need to co-design the algorithm and system stack to enable TinyML. In this review, we will first discuss the definition, challenges, and applications of TinyML. We then survey the recent progress in TinyML and deep learning on MCUs. Next, we will introduce MCUNet, showing how we can achieve ImageNet-scale AI applications on IoT devices with system-algorithm co-design. We will further extend the solution from inference to training and introduce tiny on-device training techniques. Finally, we present future directions in this area. Today's large model might be tomorrow's tiny model. The scope of TinyML should evolve and adapt over time.

Tiny Machine Learning （TinyML）是机器学习的新领域。通过将深度学习模型应用于无数物联网设备和微控制器（MCU），我们扩大了人工智能应用的范围并实现了无处不在的智能。然而，由于硬件限制，TinyML具有一定挑战性，因为内存资源有限，难以容纳为云和移动平台设计的深度学习模型；同时，裸机设备对编译器和推理引擎的支持有限。因此，我们需要对算法和系统栈进行共同设计，以实现TinyML。在此综述中，我们首先讨论TinyML的定义、挑战和应用；接下来，我们调查了最近在MCUs上TinyML和深度学习的进展；然后，我们介绍了MCUNet，展示了如何通过系统-算法共同设计，在物联网设备上实现ImageNet规模的人工智能应用；我们还将解决方案从推理扩展到训练，并介绍了小型设备上的训练技术；最后，我们展示了这个领域的未来发展方向。今天的大型模型可能成为明天的小型模型，TinyML的范围应该随着时间的推移而不断发展和适应。

微型机器学习：进展与前景