Affiliation:
1. Computer Science and Biomedical Informatics, University of Thessaly School of Science, Lamia, Greece and Intelligent Systems Laboratory, University of Thessaly School of Science, Lamia, Greece
Abstract
Tiny Machine Learning (TinyML) is an emerging technology proposed by the scientific community for developing autonomous and secure devices that can gather, process, and provide results without transferring data to external entities. The technology aims to democratize AI by making it available to more sectors and contribute to the digital revolution of intelligent devices. In this work, a classification of the most common optimization techniques for Neural Network compression is conducted. Additionally, a review of the development boards and TinyML software is presented. Furthermore, the work provides educational resources, a classification of the technology applications, and future directions and concludes with the challenges and considerations.
Funder
Operational Programme “Competitiveness, Entrepreneurship and Innovation”
Greece and the European Union
Publisher
Association for Computing Machinery (ACM)
Reference237 articles.
1. TinyML in Publications - Dimensions. 2022. Retrieved from https://app.dimensions.ai/discover/publication?search_mode=content&search_text=TinyML&search_type=kws&search_field=full_search
2. Mobile Edge Computing: A Survey
3. Cartoonize Images using TinyML Strategies with Transfer Learning
4. Adafruit. 2021. Adafruit EdgeBadge - TensorFlow Lite for Microcontrollers. Retrieved from https://www.adafruit.com/product/4400
5. Tiny Neural Networks for Environmental Predictions: An Integrated Approach with Miosix