Authors:- Anushka Tyagi , Rajendra Thakur , Srivesh Pandey
Authors:-The rapid growth of the Internet of Things (IoT) has necessitated the deployment of intelligent systems on resource-constrained devices. Tiny Machine Learning (TinyML) is an emerging paradigm that enables machine learning models to run on microcontrollers with limited processing power, memory, and energy budgets. This paper presents a comprehensive review of TinyML architectures designed for resource-constrained microcontrollers. It explores model optimization techniques, inference strategies, and deployment frameworks, highlighting their suitability for real-world applications such as smart homes, wearable devices, and industrial monitoring. Additionally, challenges related to energy efficiency, latency, and security are discussed. Finally, future research directions in TinyML are outlined to provide a roadmap for deploying scalable and efficient AI systems on ultra-low-power devices.
Keywords TinyML, Microcontrollers, Edge AI, Model Optimization, Resource-Constrained Devices, Energy-Efficient Machine Learning, IoT, Embedded AI
Full Issue
| View or download the full issue | PDF 1-15 |