Introduction to Deep Learning

6.S191 is MIT's introductory course on deep learning, taught during the January Independent Activities Period by Alexander Amini and Ava Soleimany. The OpenCourseWare listing currently reflects the January 2026 edition, and its only resource is a link to the course's own website, where the lecture videos, slides and software labs are published. The course covers deep learning methods and their applications to computer vision, natural language processing, biology and other areas. Students are meant to leave with foundational knowledge of deep learning algorithms and hands-on experience building neural networks in TensorFlow, and the on-campus class ends with a project proposal competition judged by staff and industry sponsors.

Stated prerequisites are calculus at the level of taking derivatives and linear algebra at the level of matrix multiplication; the instructors say they will try to explain everything else along the way, and that Python experience is helpful but not required. Compared with MIT's semester-long OpenCourseWare offerings, this is a short, intensive series: the OCW page is a gateway to the course site rather than a full set of notes, problem sets and exams, so pair it with a linear algebra or machine learning course if you want practice material. The videos, slides and labs are free, no account is needed, the course site releases its materials under the MIT licence rather than OpenCourseWare's Creative Commons terms, and no certificate is offered.