advertisement for the conference


SciTinyML: Scientific Use of Machine Learning on Low-Power Devices will be run virtually from October 18-22, 2021.
The Zoom link was sent out to all registered attendees. Please check your email and/or sign up for our workshop.

SciTinyML is an ICTP Virtual Meeting supported by the TinyML4D Academic Network and open to all.

Embedded machine learning (tinyML) enables machine learning technologies to perform on-device analytics of sensor data at extremely low power. This allows for new scientific applications to be developed at an extremely low cost and at large scale.

In recent years, hardware advancements have made it possible for microcontrollers to perform calculations much faster. Improved hardware has made it easier for developers to build programs on these devices. Perhaps the most important trend for scientists has been the rise of embedded machine learning, or tinyML.

Between hardware advancements and the tinyML community’s recent innovations in machine learning, it is now possible to run increasingly complex deep learning models directly on microcontrollers. tinyML represents a collaborative effort between the embedded power systems and machine learning communities, which traditionally have operated independently.


  • Introduction to Embedded ML (tinyML)
  • Examples of tinyML applications
  • Scientific Applications of ML
We have also held 3 seminars leading up to the workshop. If you missed any of the seminars you can find the recordings on the TinyML4D Past Events page.

Workshop Schedule

View the Detailed Schedule

Day Date Topics Speakers
Day 1 Monday Introduction to Embedded ML (tinyML) Vijay Janapa Reddi of Harvard University and Laurence Moroney of Google
Day 2 Tuesday Hands on Embedded ML - Vision and Audio Brian Plancher and Mark Mazumder of Harvard University
Day 3 Wednesday Sensors and Ethical Issues for ML and IoT Serge Stinckwich and Attlee Gamundani of United Nations University Institute in Macau and Sebastian Büttrich of IT University of Copenhagen
Day 4 Thursday Hands on Embedded ML - Motion/Anomaly Detection and Scientific Applications Marcelo Rovai of UNIFEI and Matthew Stewart of Harvard University
Day 5 Friday Academic Network Next Steps and Closing Keynotes Marco Zennaro of ICTP, Hal Speed of Robotical, Susan Kennedy of Santa Clara University, and Pete Warden of Google


Contact with any questions regarding this workshop.


We would like to thank Harvard SEAS, tinyML Foundation, ICTP, Edge Impulse, Google, and the TensorFlow Lite Micro Team for the continued support of all of our TinyML educational content!