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
- 3
- Core units
- 38
Curriculum · 01—07
Choose your starting point
Seven connected stages, from practical foundations to the mechanics behind modern language models.
Python & Data Foundations
Learn enough Python and data tooling to inspect, clean and explain a real dataset.
Mathematics for Machine Learning
Build the linear algebra, calculus, probability and optimization intuition needed to understand how machine-learning models represent data and learn from it.
Algorithms & Data Structures
Reason about the data structures and algorithms behind efficient programs.
Classical Machine Learning
Learn to frame tabular prediction problems, build leakage-safe scikit-learn pipelines, compare classical model families and evaluate their errors responsibly.
Deep Learning with PyTorch
Understand neural networks and train them with PyTorch.
Systems Foundations
Understand the operating-system, networking and hardware concepts behind AI workloads.
LLM Foundations
Understand the architecture and execution of modern language models.