Intelligence at the Extreme Edge: A Survey on Reformable TinyML

Abstract

Tiny Machine Learning (TinyML) is an upsurging research field that proposes to democratize the use of Machine Learning and Deep Learning on highly energy-efficient frugal Microcontroller Units. Considering the general assumption that TinyML can only run inference, growing interest in the domain has led to work that makes them reformable, i.e., solutions that permit models to improve once deployed. This work presents a survey on reformable TinyML solutions with the proposal of a novel taxonomy. Here, the suitability of each hierarchical layer for reformability is discussed. Furthermore, we explore the workflow of TinyML and analyze the identified deployment schemes, available tools and the scarcely available benchmarking tools. Finally, we discuss how reformable TinyML can impact a few selected industrial areas and discuss the challenges and future directions.

References in corpus (9)

• AI for Next Generation Computing: Emerging Trends and Future Directions
• Machine Learning for Microcontroller-Class Hardware: A Review
• TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems
• MicroNets: Neural Network Architectures for Deploying TinyML Applications on Commodity Microcontrollers
• A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays
• Visual Wake Words Dataset
• A Tiny CNN Architecture for Medical Face Mask Detection for Resource-Constrained Endpoints
• TinyML for Ubiquitous Edge AI
• TinyFedTL: Federated Transfer Learning on Tiny Devices

Cited by in corpus (3)

• TinyML: Tools, Applications, Challenges, and Future Research Directions
• On-device Online Learning and Semantic Management of TinyML Systems
• From Tiny Machine Learning to Tiny Deep Learning: A Survey