Tiny Machine Learning for Resource-Constrained Microcontrollers

Abstract

We use 250 billion microcontrollers daily in electronic devices that are capable of running machine learning models inside them. Unfortunately, most of these microcontrollers are highly constrained in terms of computational resources, such as memory usage or clock speed. These are exactly the same resources that play a key role in teaching and running a machine learning model with a basic computer. However, in a microcontroller environment, constrained resources make a critical difference. Therefore, a new paradigm known as tiny machine learning had to be created to meet the constrained requirements of the embedded devices. In this review, we discuss the resource optimization challenges of tiny machine learning and different methods, such as quantization, pruning, and clustering, that can be used to overcome these resource difficulties. Furthermore, we summarize the present state of tiny machine learning frameworks, libraries, development environments, and tools. The benchmarking of tiny machine learning devices is another thing to be concerned about; these same constraints of the microcontrollers and diversity of hardware and software turn to benchmark challenges that must be resolved before it is possible to measure performance differences reliably between embedded devices. We also discuss emerging techniques and approaches to boost and expand the tiny machine learning process and improve data privacy and security. In the end, we form a conclusion about tiny machine learning and its future development.

Vehicle Surroundings Perception Using Micro‐electromechanical Systems Inertial Sensors

“…However, general-purpose microcontrollers have very limited resources which pose a challenge to deep neural networks. [16,17] To address this challenge, we extend the concept of smart MEMS sensors further by integrating a hardware accelerator for CNNs.…”

A Machine Learning-Oriented Survey on Tiny Machine Learning

“…MCU and TinyML are the subjects of [28], [33], [34]. In [28], the authors analyze the TinyML frameworks for integrating ML algorithms within MCUs and present a realworld case study.…”

“…TinyML heavily depends on hardware devices to enable efficient training and inference for its applications. Based on our literature research [28], [33], [33], [34], [41], [42], in this section, we will examine processors for TinyML workloads spanning from general-purpose Central Processing Units (CPUs) to more programmable and adaptable architectures with discussions of Graphics Processing Units (GPUs), FP-GAs, and Tensor Processing Units (TPUs). By structuring the analysis along this range, we aim to illustrate the fundamental trade-offs between efficiency, programmability, and flexibility.…”

Universal machine learning approach to volcanic eruption forecasting using seismic features

“…This allows the surveillance team to consider the temporal evolution of a probabilistic numeric value as a reliable forecasting tool. This machine learning model is straightforward and allows its implementation in small and less powerful devices; the algorithm focusses on Tiny Machine Learning applications, to achieve the minimum of computation power and time required for analysing the data (Immonen and Hämäläinen, 2022).…”