EECS 182/282A: Deep Neural Networks
Fall 2026 · UC Berkeley
Lectures Tuesday and Thursday, 9:30–10:59 AM, The Gateway Building 1210. Discussion sections meet on Friday; see class times for section rooms.
Deep Networks have revolutionized computer vision, language technology, robotics and control. They have a growing impact in many other areas of science and engineering, and increasingly, on commerce and society. They do not however, fully follow any currently known compact set of theoretical principles. In Yann LeCun’s words they require “an interplay between intuitive insights, theoretical modeling, practical implementations, empirical studies, and scientific analyses.” This is a fancy way of saying “we don’t understand this stuff nearly well enough, but we have no choice but to muddle through anyway.” This course attempts to cover that ground and show students how to muddle through even as we aspire to do more. That said, we will be leveraging the substantial, though still tentative, understanding that we have gained in the past few years. It isn’t 2015 anymore — we know a lot more than we used to.
Some Fall 2026 logistics are still being finalized: office hours, the graduate student instructor roster, and the Ed and Gradescope join links will be posted here before instruction begins on August 26.
Start here
- The schedule lists every lecture, discussion section and homework deadline for the semester.
- Class times has the lecture room and all six section times.
- The syllabus covers prerequisites, grading, and course policies. Read it before the first lecture.
- The staff page lists instructors and office hours.
- Homework 0 is due Friday, September 4 and is how we judge engagement for enrollment purposes. See the enrollment policy.
Getting set up
Lectures are webcast by the department and recordings are posted to a YouTube playlist;
you must be signed in to your @berkeley.edu account to view them. Homework is submitted
on Gradescope, and all course discussion and announcements happen on Ed. Join links for
Fall 2026 will be posted on this page and announced in the first lecture.
GPU and CPU compute for assignments is available through the compute portal.