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

ML07 · Learning in Special Settings

A free, illustrated L3 course of 10 modules in the Machine Learning track. Modules include: Semi-supervised learning; Active learning; Weak supervision and noisy labels.

ML07 L3 · Advanced 10 modules · about 40 lessons Planned · Ring 3

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

Modules

1. Semi-supervised learning
2. Active learning
3. Weak supervision and noisy labels
4. Transfer and domain adaptation
5. Distribution shift
6. Online and streaming learning
7. Learning to rank
8. Fraud and rare-event detection
9. Federated learning
10. Fairness-aware learning

Signature illustrations

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

A taxonomy of shift types, query regions in active learning, one federated training round as a schematic.

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.