Must be in the Graduate Program in Computer Science. All other graduate students must request permission.

This course is an introduction to differentiable Programming, a new programming paradigm in which a numerical program can be differentiated through automatic differentiation , allowing gradient-based optimization of parameters in the program. It has broad applications in Computer Graphics, Computer Vision, Deep Learning, Quantum Computing, System Control, and many more. The course assumes a good working knowledge of linear algebra and differentiation. The course experience includes hands-on project s with differentiable programming for agentic AI systems and physical intelligence.