Skip to main content

Introduction to Learing Session 😎

TinyML is a field of study in Machine Learning and Embedded Systems that explores the types of models you can run on small, low-powered devices like microcontrollers. It enables low-latency, low power and low bandwidth model inference at edge devices. While a standard consumer CPUs consumes between 65 watts and 85 watts and a standard consumer GPU consumes anywhere between 200 watts to 500 watts, a typical microcontroller consumes power in the order of milliwatts or microwatts.

That is around a thousand times less power consumption. This low power consumption enables the TinyML devices to run unplugged on batteries for weeks, months, and in some cases, even years while running ML applications on edge. (src:towardsdatascience)

Procedure ⛓

  • Co-learners onboarding: Participants need to register as co-learner.
  • Weekly Learning Session: Each week, there will be a learning session.
  • Weekly Assignments: Each week, participants will get an assignment, and they need to submit it the following week.
  • Industry sessions: There will be sessions from industries such as Realtek or MediaTek to share industry perspectives on the tinyML and related technologies.

Materials & Resources 📚

This web page will manage all the learning material and resources.

Resource Link 🌐

  • Introduction to TinyML Slide By Accomdemy - Slide
  • Tiny Supported Hardware List - List