Save this video free

CMU Introduction To Deep Learning 11-785, Fall 2026: Lecture 22

Carnegie Mellon University Deep Learning · 1:28:26 · 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 derives the variational autoencoder (VAE) as a generative model: a decoder maps a Gaussian latent space onto a learned low-dimensional data manifold, while output noise accounts for variation away from that manifold. It builds the training objective from reconstruction likelihood and KL regularization, explains the Gaussian approximate posterior and reparameterization trick, and closes with MNIST and face-generation examples, latent-space interpolation, and the limits of blurry VAE outputs.

Key takeaways

Chapters

0:00 Lecture Setup and Audio-Visual Checks
6:23 From Autoencoders to Learning a Data Distribution
8:46 Structured Images Occupy a Small Part of Pixel Space
13:35 Low-Dimensional Latents Map to Curved Data Manifolds
16:43 An Autoencoder Decoder Learns the Principal Manifold
22:04 Unconstrained Latents Create Disconnected Regions and Strange Samples
27:17 A Gaussian Prior Regularizes the Latent Space
29:11 Gaussian Density Connects Latent Regularization to KL Divergence
33:24 The Decoder Warps Both Manifold Shape and Probability Density
40:40 Off-Manifold Gaussian Noise Models Data Variation
45:51 The Generative Story Requires a Latent Posterior
50:10 The Encoder Estimates a Distribution over Latent Codes
54:53 The VAE Objective Balances Posterior Fit and Prior Matching
1:06:27 A Gaussian Approximation Makes the Posterior Trainable
1:10:03 Reconstruction Likelihood and the Reparameterization Trick
1:15:47 VAE Loss Combines Reconstruction, KL, and Variance Terms
1:24:53 MNIST, Face Interpolation, and the Path to Latent Diffusion

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

Transcript excerpt

0:06 That's about it. And then I usually like for him I usually keep it at a wide shot so you can see the slides a nice shot but then zoom in when but then zoom in when he's writing on the board. >> Again like with the recitation they usually don't keep the board. You probably just keep it >> scares me. Te has those converters on top of the I think they're >> stabilizer. Yeah, the NDI. Are those that NDX encoder? NX. No, you're good.

0:58 >> Yeah, I got it. >> No problem. >> All right, there you go. You should be all set. >> Thank you very much. Yeah, they they have the microphone >> pretty well. >> Oh. Oh. Byebye. right here. >> How's it going?

2:19 orange Good. >> Yeah. combination. >> Yeah. Couple

3:23 extra Those are good. That's

6:23 Okay, good morning everybody. My machine's been crashing since last night. So, ah, it's nice to look up and actually see faces. And you've gone over there. >> Yeah. Anyways, uh we're going to start a new series of topics for the next uh four lectures. This is actually a continuation of what we did in the last class. What was the last topic we covered? >> Autoenccoder. What did we learn at the end of the class? What does the autoenccoder learn? >> Is that what the autoenccoder learned?

7:17 >> It's been two days. So, somebody has to give me the correct answer. What did the autoenccoder learn? small >> small representation but what else did it learn >> principle but was it pl is it was it linear >> so what exactly did the autoenccoder learn >> nonlinear features >> is it a nonlinear representation of features or is there was there a little more

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.