SciTinyML-23: Scientific Use of Machine Learning on Low-Power Devices

A TinyMLedu Workshop

Spring/Summer 2023

SciTinyML-23: Scientific Use of Machine Learning on Low-Power Devices

A TinyMLedu Workshop

Spring/Summer 2023

Course Overview

SciTinyML-23 was an ICTP Virtual Meeting supported by the TinyML4D Academic Network and open to all exploring how embedded ML (tinyML) can impact the developing world through hands-on activities using embedded hardware devices. SciTinyML-23 was attend by 418 participants from 76 countries. The 2023 theme was Applications and Advanced Topics. We still began the workshop with our usual open introduction to TinyML through Hands-on Labs on Days 1 and 2 to get everyone up to speed and then will transition toward more application focused and advanced topics. This program was a collaboration led by the Abdus Salam International Centre for Theoretical Physics (ICTP), the Harvard John A. Paulson School of Engineering and Applied Sciences, Barnard College of Columbia University, Universidade Federal de Itajubá (UNIFEI), and TinyMLedu.

TinyML is a subfield of Machine Learning focused on developing models that can be executed on small, real-time, low-power, and low-cost embedded devices. This allows for new scientific applications to be developed at an extremely low cost and at large scale. TinyML represents a collaborative effort between the embedded power systems and Machine Learning communities, which traditionally have operated independently. TinyML has a significant role to play in achieving the SDGs and facilitating scientific research in areas such as environmental monitoring, physics of complex systems and energy management. The TinyML process starts with collecting data from IoT devices, then training the collected dataset to extract knowledge patterns; these patterns are then packaged into a TinyML model that considers the target microprocessor’s limited resources such as memory, processing power, and energy.

Workshop topics included an intorduction to (tiny)ML concepts, getting started with the TinyML training kit, examples of TinyML applications, the tinyML development workflow, scientific applications of ML, and recent research and advanced topics in TinyML.

My Roles