UROP Openings

Have a UROP opening you would like to submit?

Please fill out the form.

Submit your UROP opening

AI-driven bicycle design (Remote)


Term:

Fall

Department:

2: Mechanical Engineering

Faculty Supervisor:

Faez Ahmed

Faculty email:

faez@mit.edu

Apply by:

09/18/2020

Contact:

Faez Ahmed: faez@mit.edu

Project Description

The goal of the project is to synthesize new bicycle designs using Machine Learning methods. Specifically, the project aims at analyzing large datasets of bicycle models and then learning to synthesize new bicycle models. A key challenge will be to encode expert and physics-based knowledge into the synthesis of new designs. Your tasks will range from using ML methods for representation learning, data augmentation, and visualization to understanding how real-world bicycles work. You will work with a Ph.D. student on this project.

Pre-requisites

- Experience in using Python - Some experience in using Machine Learning libraries like Scikit-Learn, TensorFlow, or Pytorch.