11.S198J / 11.S955J
Deep Learning for Transportation

Prerequisites: 
6.001 Python and 6.036 Introduction to Machine Learning or equivalent

Explores deep learning (DL) methods for urban transportation applications. Covers concepts of algorithmic prediction, interpretability, causality, and fairness in the context of mobility system design and policy making. Topics include travel demand prediction at both individual and aggregate levels, decision with and without uncertainty, vehicle and ride sharing, traffic prediction and control, and multimodal system design. Students learn intuitions and methods in DNN, CNN, RNN and reinforcement learning, build hands-on models using real-world datasets, and design and implement team-based term projects. At the intersection of machine learning methods and transportation applications, the course seeks to reconcile the tension between generic-purpose models and domain-specific knowledge. Furthermore, the course critically envisions and reflects on how machine learning methods shape transportation research and mobility industry, and examines the potentials and pitfalls of their applications in transportation policy making.