Annotated Deep Learning Course
For the past five years, one of the most enjoyable things I've done outside of my day job is teaching. From 2020 to 2025, I had the pleasure of teaching a course in the Master of Management Analytics (MMA) program at the Rotman School of Management (UofT). Now that I've wrapped up that course (on to the next one), I decided to package up the material and put it online for posterity.
You can find the full set of annotated lecture notes here: dlcourse.bjlkeng.io.
The Evolution of the Course
When I first took on the class, it was officially listed as a marketing analytics course. However, I pivoted it into a deep learning course with applications in marketing. By the end of my run, the syllabus ended up being roughly a 70/30 split between core deep learning concepts and marketing-related topics. The version I've hosted online is the final iteration from the 2025 course.
The audience for this class was primarily professional master's students, typically zero to two years out of their undergrad. Most of them didn't come from a pure computer science background, but rather technical-adjacent fields like statistics, engineering, or economics. Because of this, my focus was always on capturing the core intuition of each topic rather than getting bogged down in deep math or rigorous proofs. To be honest, extracting and explaining those high-level ideas is the most fun part of teaching anyway!
A Quick Disclaimer
As anyone following the space knows, AI has progressed at a blistering pace over the last few years. Because of that, some of the material in these notes is inevitably a bit (or a lot) out of date. Still, the fundamental intuitions and core concepts remain highly relevant.
I'm putting this up mostly as an archive of the work I put into the class, but I hope it still serves as a useful resource for anyone looking to build a conceptual understanding of deep learning.
If you end up checking it out and find it helpful, feel free to drop me a note!