ML01 · Machine Learning Foundations
A free, illustrated L1 course of 10 modules in the Machine Learning track. Modules include: What learning from data means; Data splits and the generalization gap; k-nearest neighbors.
ML01 L1 · Core 10 modules · about 40 lessons 10 of 10 modules live
Part of the Machine Learning track. Ships in Ring 1 (Foundation) of the roadmap.
Modules
- What learning from data means Live · 4 lessons
- Data splits and the generalization gap Live · 4 lessons
- k-nearest neighbors Live · 4 lessons
- Linear regression as a learning algorithm Live · 4 lessons
- Gradient descent from scratch Live · 4 lessons
- Logistic regression and classification Live · 4 lessons
- Evaluation metrics Live · 4 lessons
- Overfitting, bias and variance Live · 4 lessons
- Regularization and validation Live · 4 lessons
- A full project from raw data to report Live · 4 lessons
Signature illustrations
The pictures a learner should still see in their head a year later:
Decision-boundary explorers, training and validation curves, bias-variance decomposition, anatomy of a confusion matrix, ROC and precision-recall curves built point by point.
Status
10 of 10 modules are written and live. The rest follow in Ring 1.
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.