Skip to main content
BitsNotes

Unsupervised Deep Learning

16 lectures

Representation learning and deep generative models, covering autoencoders, VAEs, GANs, normalizing flows, and diffusion models.

01Lecture 01 · Unsupervised Deep Learning: Course Overview
02Lecture 02 · Generative Modeling Goals and Principal Component Analysis
03Lecture 03 · PCA Variants and Autoencoders
04Lecture 04 · Regularized Autoencoders and Likelihood-Based Generative Models
05Lecture 05 · Building Autoregressive Models
06Lecture 06 · PixelCNN Variants and 1D Normalizing Flows
07Lecture 07 · Normalizing Flow Models
08Lecture 08 · Normalizing Flows: Masked Autoregressive Models
09Lecture 09 · Variational Autoencoders
10Lecture 10 · Discrete Latent Spaces and Generative Adversarial Networks
11Lecture 11 · Improving GAN Training: Optimal Discriminators, DCGAN, and the Wasserstein Distance
12Lecture 12 · Variants of Generative Adversarial Networks
13Lecture 13 · From CycleGAN to Diffusion Models
14Lecture 14 · Diffusion Models and Energy-Based Models
15Lecture 15 · Energy-Based Models and Natural Language Processing Applications
16Lecture 16 · BERT, GPT, and Vision-Language Models
Loading comments…