CHAPTER 01
Complete
Foundations
Core building blocks and fundamental data terminology
DatasetSampleFeatureLabelTraining SetValidation SetTest Set+6
Read (13 sections)
A structured, interview-ready reference covering core machine learning concepts with mathematical derivations, intuitive mental models, production applications, and common pitfalls.
These notes represent my own study jottings and learning synthesis, not an authoritative or foolproof standard. If you find them helpful, feel free to use them. If you spot anything that could be clearer or have suggestions for additional concepts to include, issues and pull requests are warmly welcome.
Core building blocks and fundamental data terminology
End-to-end lifecycle and phases of an ML project
Continuous numerical prediction and first-order optimization
Categorical decisions, probabilities, and decision boundaries
Generalization error, decomposition, and model capacity
Computational graphs, tensors, and the autodiff training loop