A personal study route through ML and AI
One finite route
through ML and AI
Start with practical Python and data work, build a first machine-learning model, then deepen the mathematics, algorithms and systems behind modern AI. Every unit says what to open, how far to go, how to practise and when to stop.
- Core stages
- 7
- Sections
- 42
- Core units
- 324
Curriculum · 01—07
Choose your starting point
Seven connected stages, from practical foundations to the mechanics behind modern language models.
Programming fundamentals for Machine Learning
Start with practical Python and data tools, complete a first end-to-end machine-learning project, then deepen the runtime, interfaces, testing, concurrency and native-systems knowledge needed to engineer reliable software.
Mathematical foundations for Machine Learning
The mathematical language needed to understand, implement and diagnose learning systems.
Algorithm and DSA
Choose representations from constraints, derive invariants and proofs, implement reliable algorithms, and test them against adversarial cases.
Classical Machine Learning
Frame defensible prediction problems, implement central model families, and turn evaluation evidence into bounded decisions.
Deep Learning
Own neural mechanisms, PyTorch execution, training diagnosis, major architectures, representation learning and reliable measurement on compact models.
Systems Foundations
Trace state across processes and machines, bound concurrent work, recover durable data, and reason quantitatively about failure, reliability and trust.
LLM Foundations
Build the tokenizer-to-cached-generation path, test every causal and state boundary, and connect model quality claims to evaluation and arithmetic.