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 Data might be outdated or incorrect.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

363-1191-00L 3 Credits BSC , DR , MSC , NDS D-BAUG , D-MTEC , D-ITET , D-HEST
You're viewing possible stale or outdated data. Please check the latest semester for more up-to-date information.

#AI4Impact: Machine Learning for Social Impact

Lecturers & Examiners: Dr. George Boateng
VVZ CR n/a

Last Updated: 2026-06-03 00:07:28

Abstract

How can AI be leveraged to make real-world impact? This course will introduce students to the fundamentals of machine learning (ML) in a hands-on manner with a focus on applying them to address challenges that will impact people's lives in areas such as health, education, legal, sustainability, and the UN Sustainable Development Goals more broadly.

Objective

This course seeks to introduce students without prior machine learning (ML) experience to the fundamentals of ML and give them hands-on skills to apply ML to solve problems that make real-world impact. Students will learn machine learning concepts such as classification, regression, deep learning, natural language processing, generative AI, and agentic AI, and apply them to real-world datasets in hands-on labs through building ML pipelines. Furthermore, students will collaborate in teams to develop ML systems that address a real-world social impact problem. The hope is that learners will leave the course adequately equipped and inspired to use their newly acquired ML superpowers to make the world a much better place! *Specific Learning Objectives* - Explain machine learning techniques (e.g., regression, classification, deep learning, NLP, generative AI, and agentic AI) and apply them to real-world datasets. - Design and implement end-to-end machine learning pipelines, including data preprocessing, feature engineering, model training, and evaluation. - Conduct thorough experiments to evaluate model performance using appropriate metrics. - Develop a machine learning system addressing a real-world social impact problem. - Collaborate effectively in teams, demonstrating project management, presentation, and scientific writing skills.

Content

This course introduces students without prior machine learning (ML) experience to the fundamentals of ML and gives them hands-on skills to apply ML to solve problems that make real-world impact. Strong programming experience in Python is a requirement. No prior experience with machine learning is required. The course is structured into Foundations and Project. *Foundations (Week 1 - 4)* The foundation consists of lectures with in-class hands-on coding exercises. In the lectures, the students will be introduced to the fundamentals of ML along with relevant applications. Emphasis will be placed on facilitating an intuitive and hands-on understanding of ML models and how to make them work on messy real-world datasets and contexts. Various topics include algorithms for classification, regression, deep learning, natural language processing, generative AI, agentic AI, and ML pipelines consisting of data exploration and preprocessing, feature extraction and engineering, model training, and evaluation. Lectures will include in-class coding exercises and discussions. It will take place in the first month of the semester two lecture sessions per week. *Projects (Week 5 - 14)* The course project will put everything together and will be the key deliverable. Students will work collaboratively in teams to implement an ML system for social impact, write a paper on the work with the caliber to be accepted at an applied ML conference in the relevant domain, and present it. Previous projects built AI systems for biodiversity prediction, science learning support, and coding learning support. Students will be responsible for finding relevant datasets for use. We will explore collaborations with nonprofits, organizations, and companies to make available relevant datasets to use for the project. The course project will be done in self-organized teams, each consisting of 4 team members, which will help to foster collaboration, communication, and project management skills. We will also have update and feedback sessions during lecture times once every two weeks for the last 2 months of the course, where teams will present updates on the course project and get feedback from peers and the course instructor. It may feature guest lecturers (e.g., practitioners) who will give talks on ML systems that they have developed and deployed for impact.

General Information

Language
English
Levels
BSC , DR , MSC , NDS
Frequency
Yearly recurring

Examination

Type
graded semester performance

Registration & Places

Max Places
20

Course Components

Type Title Time & Place Hours
lecture with exercise #AI4Impact: Machine Learning for Social Impact No time listed 26 h semesterly

Offered In