The 15-Day Course
PART I Detailed beginner notes for every day, with worked examples, code, a quick recap and a checkpoint. Day 1 is the prerequisite day: do it even if you think you know the basics, then move on. | Day | Topic | | --- |
PART I
Detailed beginner notes for every day, with worked examples, code, a quick recap and a checkpoint. Day 1 is the prerequisite day: do it even if you think you know the basics, then move on.
| Day | Topic |
|---|---|
| 1 | Prerequisites: Python & Math Essentials |
| 2 | NumPy: Arrays, Shapes & Matrix Math |
| 3 | Pandas: Load, Clean & Prepare Data |
| 4 | Linear Regression + Gradient Descent |
| 5 | Overfitting, Regularization & Cross-Validation |
| 6 | Metrics, Decision Trees, Random Forest, Boosting |
| 7 | k-NN, k-Means, PCA, Embeddings |
| 8 | Mini Project 1: Telco Customer Churn |
| 9 | Neural Networks From Scratch |
| 10 | Backpropagation: How a Network Learns |
| 11 | PyTorch |
| 12 | MNIST, Dropout, Early Stopping, CNN |
| 13 | Attention & Transformers ★★★ |
| 14 | Capstone + Recap |
| 15 | What Comes Next: GenAI Bridges & Study Toolkit |
A flexible schedule Treat the 15 days as a guided roadmap, not a promise of mastery. Many readers need 2–3 days for Days 9–10 and for Day 13, and that is normal. Optional revision days: after Day 6 (classical ML), after Day 10 (neural networks), and after Day 13 (Transformers). Use them to redo the worked problems you got wrong and to re-run your own code. Each day ends with a “Move on when you can…” checklist. Use it, not the calendar, to decide when to continue.