We live in incredible times. So many technologies are being developed right now that have the potential to affect our everyday lives in many positive ways. Quantum computing, machine learning, strong artificial intelligence, blockchain, internet of things, etc., we all have heard about these technologies, and now I’d like to bring the attention to another technology that also has the potential to affect our lives – TinyML.
Professor Janapa Reddi at John A. Paulson School of Engineering and Applied Sciences at Harvard University makes the following definition: “Tiny machine learning (TinyML) is a fast-growing field of machine learning technologies and applications including algorithms, hardware, and software capable of performing on-device sensor data analytics (vision, audio, motion, etc.) at extremely low power, typically in the milliwatt (mW) range and below, and hence enabling a variety of always-on applications.”
Let’s break down this definition into two important concepts. First, machine learning is a branch of artificial intelligence research in which advanced algorithms improve or “learn” through experience. These algorithms build models based on processing large datasets. Then these models are used to make decisions, usually on real-time input data.