Math Foundations
3 topics · 5 weeks
Build the statistical intuition ML rests on.
Vectors, matrices, eigenvalues.
Gradients, optimization.
Python Data Stack
4 topics · 5 weeks
Wrangle and explore data.
Machine Learning
3 topics · 6 weeks
Train and evaluate classical models.
Encoding, scaling, selection.
Cross-validation, metrics, bias/variance.
Deep Learning & NLP
3 topics · 6 weeks
Neural networks and modern AI.
Attention, fine-tuning, RAG.
Production ML
3 topics · 4 weeks
Ship models, not notebooks.
APIs, batch vs real-time.
Retraining, data drift detection.
Data Scientist
Data science blends math, programming, and domain insight. This path builds the statistical foundation first, then the Python data stack, then models — ending with deploying them.
7–10 months · 5 stages · 16 topics
Stages
Click a topic to open its notes. Drag to pan, scroll to zoom; dashed topics are optional.