Save this video free

CMU Introduction To Deep Learning 11-785, Fall 2026: Lecture 24

Carnegie Mellon University Deep Learning · 1:30:09 · Watch on YouTube

Part of Carnegie Mellon University 11-785 Introduction to Deep Learning. See all 24 lectures and search them

These notes were made with YouTube Collector. Paste any YouTube link and get the same: a summary, chapters and a searchable transcript.

Overview

The lecture develops Generative Adversarial Networks (GANs) from their motivation: maximum-likelihood training of a VAE-style generator does not directly test whether novel samples look like the training data. It explains the generator-discriminator minimax game, derives the optimal discriminator and the connection between the original GAN objective and Jensen-Shannon divergence, then motivates Wasserstein GANs with a 1-Lipschitz critic to provide useful gradients when distributions have disjoint support.

Key takeaways

Chapters

0:00 Before Class: Campus Chatter and Attendance
6:26 Reviewing Generative Models and the Previous Diffusion Lecture
10:08 The VAE Generator: Transforming Gaussian Noise into Data
13:22 Why Likelihood Training Does Not Guarantee Realistic Novel Samples
20:42 GANs Add a Learned Test for Whether Generated Data Looks Real
27:16 Training the GAN Discriminator on Real and Generated Examples
32:48 The Original GAN Minimax Objective and Alternating Updates
38:47 The Optimal Discriminator Estimates Real-Data Probability
42:31 How Alternating Generator and Discriminator Updates Align Distributions
48:40 Deriving the GAN Objective’s Jensen-Shannon Connection
57:26 GAN Equilibrium, Vanishing Gradients, and Training Instability
1:01:18 VAE and GAN Tradeoffs: Blurry Samples Versus Training Difficulty
1:04:08 Why Saturated or Weak Discriminators Starve the Generator of Gradients
1:08:31 Disjoint Supports Make KL and JS Gradients Uninformative
1:13:35 Earth Mover Distance Measures the Work to Move Probability Mass
1:18:27 Optimal Transport Plans Define the Wasserstein Distance
1:21:57 Kantorovich-Rubinstein Duality Leads to the WGAN Critic
1:29:18 WGAN Gradient Penalty and Final Notes on Mode Collapse

Keep these chapters and the full searchable transcript in your own library.

Transcript excerpt

0:24 For the first time in my life, I understood why levels where distance I saw a video starting quantum of quantum theory course and I said uh apparently only I the only one does not know quantum theory at the end of the course like everybody and then you just go around spreading your misinformation. >> So this lecture I used to just outsource it every single semester because when you don't want to learn something outsource it nobody wanted to pick it up

1:11 this time. I have no choice. Now I have to learn. I spend the night learning stuff and discovering I forgotten things I learned in college programming. How do you do the duos? What's the theory behind it? It's always vague when I'm going back and looking at This girl always has the most amazing dresses. >> I know. Every single day. >> Very amazing. >> I always tell her dress always pretty.

1:59 >> I don't know where she gets them from. >> She looks a little bit like a fairy. She >> does. So, >> it's so easy to spot men no matter where she is. >> She's the one with the unique dress. >> Yeah. Well, you got incredible taste and you have and you can pull it off this sweater. But I've been wearing it for a long time. But you know someone in 2018 LTI has these uh once a semester once a year they have post lunch where the professors serve the students. So I went out there and served the students and somebody uh took

2:49 a picture of me and posted it on Piaz a cute bra. So you know you remember this right? I just I just remember this when I wrote this letter. She says it was 8

This is the start of the transcript. Save this video free for the whole transcript, searchable and time-coded.

In this course

Related notes

Summary, takeaways, and chapters were generated by AI from the video's transcript and may contain errors. The video belongs to its creator, Carnegie Mellon University Deep Learning.

Want the full transcript?

Save this video in YouTube Collector to get its complete searchable transcript, your own AI summaries, and a library that keeps every video you collect in one place.