advertisement for the workshops


SciTinyML: Scientific Use of Machine Learning on Low-Power Devices will be run remotely in English for 2023 from April 17-21.
Register to attend for free by Friday, April 7, 2023 on the ICTP website!
We are also actively soliciting submissions for short talks during our Show and Tell day! Please follow this link to learn more!

To view the materials and videos from past years SciTinyML workshops and TinyML4D seminars please visit the TinyML4D Past Events page.

This year’s theme is Applications and Advanced Topics. We’ll still begin 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 (see the schedule below for more details).

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

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.

Through hands-on examples, this workshop will focus on both introductory and advanced topics in TinyML to pave the way to the development of real-world applications.

Workshop Topics:

  • Introduction to TinyML
  • Getting Started with the TinyML Kit
  • Examples of TinyML Applications
  • The TinyML Development Workflow
  • Scientific Applications of ML
  • Recent Research and Advanced Topics in TinyML


Draft Schedule Subject to Change

Day Date Topics Speakers and Materials
Day 1 Monday Introduction to (tiny)ML
   1:00:00 PM  Workshop Opening and Schedule
   1:30:00 PM  Opening Keynote
   2:15:00 PM  Introduction to Machine Learning
   3:15:00 PM  Introduction to Embedded ML
   3:55:00 PM  Day Closing

Day 2 Tuesday Hands-on Introduction to TinyML
   1:00:00 PM  Day Opening
   1:05:00 PM  Edge Impulse Overview and New Features
   1:35:00 PM  Hands-on Motion Classification and Anomaly Detection
   3:00:00 PM  Leveraging Other Microcontrollers and Sensors
   3:55:00 PM  Day Closing

Day 3 Wednesday From Demos to Applications
   1:00:00 PM  Day Opening
   1:05:00 PM  MLOps: Scaling Deployments
   1:35:00 PM  To Personalize or Not To Personalize?
     Soft Personalization and the Ethics of ML for Health
   2:25:00 PM  WebUSB and FOMO
   2:55:00 PM  Industry 5.0 with Jetson Nano
   3:25:00 PM  Adding IoT to a Project with Blues Wireless
   3:55:00 PM  Day Closing

Day 4 Thursday TinyML Show and Tell
   1:00:00 PM  Day Opening
   1:05:00 PM  Show and Tell Introduction
   1:10:00 PM  Smart Poultry Farm
   1:30:00 PM  Wildlife Movement and Foraging Analysis
   1:50:00 PM  A TinyML Personal Trainer
   2:10:00 PM  Sleep Apnea Detection
   2:30:00 PM  Rainfall Estimation from Audio Data
   2:50:00 PM  Crop Disease Classification
   3:10:00 PM  Word Recognition in Kichwa
   3:30:00 PM  Digital Signal Processing
   3:50:00 PM  Day Closing

Show & Tell Presentations of Universities
Day 5 Friday Advanced Scientific TinyML
   1:00:00 PM  Day Opening
   1:05:00 PM  TinyML and Robotics
   1:50:00 PM  Machine Learning Sensors
   2:35:00 PM  TinyML and Sustainability
   3:05:00 PM  Workshop Closing and Future Events
   3:25:00 PM  TinyML4D Regional Networking


Contact with any questions regarding this workshop.


We would like to thank ICTP, Harvard SEAS, Barnard College, the Universidade Federal de Itajubá, and the tinyML Foundation for their continued leadership and support of all of our TinyML educational content!