Data Science in Action

Machine Learning for Self-Driving Cars

A four-week program to introduce programming and machine learning to high school students


Apply Now

The objective of the program is to introduce students to statistics, machine learning, and programming through a project in which they program machine learning algorithms to recognize images and make a self-driving toy car. Our mission is to give young students opportunities to learn about AI/ML and to allow students from diverse backgrounds to have more opportunities to access quality education.

The camp consists of two parts. 

In Part 1 (July 21- August 1, 2025), students will be introduced to the Python programming language through self-paced virtual classes which provide a foundation to implement the conceptual-level statistical, machine learning and programming components. Tutorials will also be available on our camp’s YouTube channel, and students can receive support through Zoom office hours with program TAs.

In Part 2, (August 4 - August 15, 2025), students will meet in person to be introduced to various machine learning methods and algorithms as well as their applications in different fields, including biomedicine. In this 2-week portion of the program, students will participate in teams, working together on programming exercises that range from coding introductory tasks to image classification. Each team will receive a laptop, a Raspberry Pi, and materials to construct a toy car. Teaching assistants will be available to provide hands-on programming and technical support throughout the in-person camp.

For the final presentation demo, the students will take pictures of physical objects and train their own classification algorithms, including neural networks, to recognize these objects. Once they achieve high-quality performance, they will install their program into a toy car equipped with a camera which will self-drive using their programmed neural network. Lunch hours will include conversations with machine learning experts from academia and industry who will share their life experiences and perspectives on data science. Complimentary lunch will also be provided.

Part 1: Online instruction with Zoom office hours (July 21 - August 1, 2025)

Part 2: In-person Day camp (August 4 - August 15, 2025)

(Note: No housing provided)

Registration Deadline: April 1, 2025

Upon acceptance, a registration fee of 50$ is required to confirm your enrollment in the summer camp.   All materials for the camp will be provided during the event. Refunds for registration costs are available for students from low-income families (full attendance and successful completion of the course required). Learn more about supporting the community here.

Locations: Countway Library, 10 Shattuck St, Boston, MA

Tuition: Tuition for the program is free. All materials for the camp will be provided during the event. Stipends are available for students from low income families (full attendance and successful completion of the course required)

Eligibility Requirements:

The program is hosted by the Translational Data Science Center for a Learning Health System (CELEHS) at the Harvard T.H. Chan School of Public Health and Harvard Medical School. It is co-sponsored by the Prediction Analytics Research Solution and Execution (PARSE), a non-profit research organization. It is taught by a team of data science researchers including faculty members from Harvard and the University of Toronto. Teaching assistants will provide hands-on programming and technical support throughout the camp.

For more information, please contact Amanda King (amking@hsph.harvard.edu) or Mohammed Moro (mohammed_moro@hms.harvard.edu).

Program Directors: Tianxi Cai and Jessica Gronsbell

Program Deputy Director: Vidul Ayakulangara Panickan

Program Staff: Amanda King and Mohammed Moro

Sponsors: Support for the program is provided by CELEHS Summer Camp Fund, CELEHS, Harvard Medical School, Harvard T.H. Chan School of Public Health, and PARSE.