Machine Learning in Resource-Scarce Embedded Systems, FPGAs, and End-Devices: A Survey

TLDR

The rapid growth of IoT devices and data traffic has driven machine learning from cloud‑centric systems to increasingly resource‑constrained edge devices, yet models are still largely viewed as requiring powerful computing platforms. This survey examines optimizations, algorithms, and platforms for deploying machine learning on highly resource‑scarce microcontroller units, offering guidelines, taxonomies, concepts, and future directions to decentralize network intelligence. The authors review and classify the techniques and hardware platforms—such as FPGA, ASIC, and MCU‑based solutions—used to implement machine learning models at the network edge.

Abstract

The number of devices connected to the Internet is increasing, exchanging large amounts of data, and turning the Internet into the 21st-century silk road for data. This road has taken machine learning to new areas of applications. However, machine learning models are not yet seen as complex systems that must run in powerful computers (i.e., Cloud). As technology, techniques, and algorithms advance, these models are implemented into more computational constrained devices. The following paper presents a study about the optimizations, algorithms, and platforms used to implement such models into the network’s end, where highly resource-scarce microcontroller units (MCUs) are found. The paper aims to provide guidelines, taxonomies, concepts, and future directions to help decentralize the network’s intelligence.