VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

227-0155-00L 6 Credits MSC , WBZ D-INFK , D-MATH , D-ITET
You're viewing possible stale or outdated data. Please check the latest semester for more up-to-date information.

Machine Learning on Microcontrollers

Lecturers & Examiners: PD Dr. Michele Magno
Does not take place this semester.
VVZ CR n/a

Last Updated: 2026-06-03 00:07:36

Abstract

Machine Learning (ML) and artificial intelligence are pervading the digital society. Today, even low-power embedded systems are incorporating ML, becoming increasingly “smart”. This lecture gives an overview of ML methods and algorithms to process and extract useful near-sensor information in end-nodes of the “internet-of-things”, using low-power microcontrollers/ processors (ARM-Cortex-M; RISC-V)

Objective

Learn how to process data from sensors and extract meaningful information using Machine Learning techniques on low-power microprocessors. We will work with real-world data from low-power sensors such as accelerometers, microphones, and cameras. The main goal is to explore how ML algorithms can be adapted to the performance constraints and limited resources of microcontrollers. You will gain hands-on experience deploying models on actual hardware platforms, understanding the importance of model and data compression, and applying various compression techniques. The course will also cover profiling and analyzing real-time inference performance, giving you practical insights into what it takes to run ML efficiently on resource-constrained embedded systems.

Content

The final goal of the course is a deep understanding of machine learning and its practical implementation on single- and multi-core microcontrollers, coupled with performance and energy efficiency analysis and optimization. The main topics of the course include: - Sensors and sensor data acquisition with low power embedded systems - Machine Learning: Overview of supervised and unsupervised learning and in particular supervised learning (Bayes Decision Theory, Decision Trees, Random Forests, kNN-Methods, Support Vector Machines, Convolutional Networks and Deep Learning) - Low-power embedded systems and their architecture. Low Power microcontrollers (ARM-Cortex M) and RISC-V-based Parallel Ultra Low Power (PULP) systems-on-chip. - Low power smart sensor system design: hardware-software tradeoffs, analysis, and optimization. Implementation and performance evaluation of ML in battery-operated embedded systems. The laboratory exercised will show how to address concrete design problems, like motion, gesture recognition, emotion detection, image and sound classification, using real sensors data and real MCU boards. Presentations from Ph.D. students and the visit to the Digital Circuits and Systems Group will introduce current research topics and international research projects.

Resources

Lecture Notes

Script and exercise sheets. Books will be suggested during the course.

General Information

Language
English
Levels
MSC , WBZ
Frequency
Semesterly recurring

Examination

Type
graded semester performance
Final grade will be based on a graded project work that can also be done in teams. The project topic can be chosen freely, as long as it employs content that is taught in this course and it employs machine learning on micro-controllers.

Registration & Places

Max Places
50

Course Components

Type Title Time & Place Hours
lecture with exercise Machine Learning on Microcontrollers
Does not take place this semester. Permission from lecturers required for all students. Takes place in the spring semester (yearly) from HS25 on.
No time listed 4 h weekly

Offered In