\( \newcommand{\vect}[1]{\mathbf{#1}} \newcommand{\mat}[1]{\mathbf{#1}} \newcommand{\R}{\mathbb{R}} \newcommand{\E}{\mathbb{E}} \newcommand{\Prob}{\mathbb{P}} \newcommand{\T}{^{\top}} \newcommand{\norm}[1]{\lVert #1 \rVert} \newcommand{\abs}[1]{\lvert #1 \rvert} \newcommand{\ihat}{\mkern1mu\hat{\boldsymbol{\imath}}\mkern2mu} \newcommand{\jhat}{\mkern1mu\hat{\boldsymbol{\jmath}}\mkern2mu} \newcommand{\pd}[2]{\frac{\partial #1}{\partial #2}} \newcommand{\argmax}{\operatorname*{arg\,max}} \newcommand{\argmin}{\operatorname*{arg\,min}} \newcommand{\cdata}[1]{\class{c-data}{#1}} \newcommand{\cmodel}[1]{\class{c-model}{#1}} \newcommand{\ctruth}[1]{\class{c-truth}{#1}} \newcommand{\cgrad}[1]{\class{c-grad}{#1}} \newcommand{\closs}[1]{\class{c-loss}{#1}} \newcommand{\cparam}[1]{\class{c-param}{#1}} \newcommand{\csecond}[1]{\class{c-second}{#1}} \renewcommand{\,}{\mkern3mu} \)

DL06 · Generative Models I

A free, illustrated L3 course of 9 modules in the Deep Learning track. Modules include: What generative modeling is; Autoregressive models; Variational autoencoders.

DL06 L3 · Advanced 9 modules · about 36 lessons Planned · Ring 3

Part of the Deep Learning track. Ships in Ring 3 (Breadth) of the roadmap.

Modules

1. What generative modeling is
2. Autoregressive models
3. Variational autoencoders
4. The ELBO in depth
5. Generative adversarial networks
6. GAN training dynamics
7. Normalizing flows
8. Energy-based models
9. Evaluating generative models

Signature illustrations

The pictures a learner should still see in their head a year later:

Latent-space interpolation grids, ELBO decomposition bars, the generator and discriminator game, a flow warping a grid step by step.

Status

This course is planned, not written yet. It ships with Ring 3 (Breadth).

Every lesson will follow the same twelve-part blueprint with at least three purpose-made figures. Watch the repository to hear when modules ship, or help write and review it.