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

DL08 · Representation and Self-Supervised Learning

A free, illustrated L3 course of 8 modules in the Deep Learning track. Modules include: What makes a representation good; Contrastive learning; Non-contrastive methods.

DL08 L3 · Advanced 8 modules · about 32 lessons Planned · Ring 3

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

Modules

1. What makes a representation good
2. Contrastive learning
3. Non-contrastive methods
4. Masked modeling
5. Vision-language pretraining
6. Multimodal foundation models
7. Transfer, probing and fine-tuning
8. Evaluating embeddings and retrieval

Signature illustrations

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

Positive and negative pair diagrams, alignment and uniformity on a sphere, masked-patch reconstruction panels, an image-text similarity matrix.

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.