Supervised Machine Learning: Course Notes, Day 1 to 12
9 posts on supervised-machine-learning, newest first.
These are my day-by-day notes from working through Andrew Ng’s Supervised Machine Learning course. They run from the first lectures to overfitting and regularization. If you’re taking the course too, start at Day 1 and read forward. If you need one topic, use the roadmap below to jump straight to the right day.
I started the course while building an AI-powered knowledge base chatbot on Django, LangChain, OpenAI, Chroma and Gradio. I wanted to understand the layer underneath the frameworks I was using. Some days were long and some got 15 minutes before bed. The notes are honest about both.
Course roadmap: what each day covers
| Day | Main topics | Post |
|---|---|---|
| 1 | Why I started the course, coming from the AI application layer | Supervised Machine Learning – Day 1 |
| 2–3 | First course videos, plus 3Blue1Brown’s “But what is a neural network?” | Supervised Machine Learning – Day 2 & 3 |
| 4–5 | Multiple features, vectorization (NumPy) | Mastering Multiple Features & Vectorization |
| 6 | Reviewing earlier notes | Supervised Machine Learning – Day 6 |
| 7 | Feature scaling, checking that gradient descent converges | Master Feature Scaling & Gradient Descent |
| 8 | Choosing the learning rate, the Jupyter lab, feature engineering | Master Learning Rate and Feature Engineering |
| 9 | Gradient descent revisited, binary classification | Master Gradient Descent and Binary Classification |
| 10 | Decision boundary, logistic regression cost function, logistic loss, gradient descent for logistic regression | Grinding Through Logistic Regression |
| 11–12 | Overfitting vs underfitting; fixing it with more data, simpler models or regularization | Overfitting! Unlocking the Last Key Concept |
Where to start
- New to the course: read Day 1 to Day 5 in order. They set up the vocabulary and the vectorized way of thinking the rest relies on.
- Stuck on gradient descent: go to Days 7–9 for feature scaling, the learning rate and how to tell whether training is converging.
- On the classification part: Day 9 introduces binary classification. Day 10 works through logistic regression end to end.
- Model fits training data but fails elsewhere: Days 11–12 cover overfitting, underfitting and regularization.
- 6 min read
Overfitting vs Underfitting & Regularization - ML Day 11-12
My Day 11-12 notes from Andrew Ng's Supervised ML course: overfitting vs underfitting, how to fix them, and regularization with λ, formulas and Python.
- 6 min read
Logistic Regression: Decision Boundary & Cost – Day 10
Day 10 notes from Andrew Ng's ML course: the logistic regression decision boundary, why squared error fails, logistic loss vs cost, and gradient descent.
- 5 min read
Gradient Descent & Logistic Regression – ML Day 9
Day 9 of Andrew Ng's Supervised ML course: gradient descent for one-variable linear regression, binary classification, logistic regression and sigmoid.
- 6 min read
Choosing the Learning Rate & Feature Engineering – Day 8
How to pick a learning rate from a learning curve, plus feature scaling and feature engineering: Day 8 notes from Andrew Ng's Supervised ML course.
- 8 min read
Feature Scaling & Gradient Descent Convergence (ML Day 7)
Day 7 notes from Andrew Ng's ML course: why feature scaling speeds up gradient descent, mean vs z-score normalization, and how to check convergence.
- 5 min read
Gradient Descent for Multiple Linear Regression: ML Day 6
Gradient descent for multiple linear regression updates every weight wⱼ by subtracting the learning rate times the average of (prediction − target) × xⱼ⁽ⁱ⁾, and updates b the same way but without the…
- 5 min read
Multiple Linear Regression & Vectorization – ML Day 4-5
Notes from Andrew Ng's Supervised ML course, days 4–5: multiple linear regression, dot product and NumPy vectorization, plus a self-quiz.
- 6 min read
Supervised ML Day 2 & 3: Gradient Descent and Learning Rate
Gradient descent minimizes a cost function J(w, b) by repeatedly moving w and b a small step against their partial derivatives, with the step size set by the learning rate α. If α is too small, it…
- 8 min read
Supervised Learning Day 1: Regression vs Classification
Supervised machine learning trains a model on labeled examples, meaning inputs (x) paired with the right answers (y), so it can predict y for inputs it hasn’t seen. Day 1 of Andrew Ng’s Supervised…
FAQ
Which course are these notes from? Andrew Ng’s Supervised Machine Learning course. The notes follow it day by day, from the first lectures through overfitting and regularization.
Do I need to take the course to follow the notes? They make the most sense next to the videos and labs. Each post also summarizes the key ideas, such as feature scaling or logistic loss, so you can use one as a quick refresher on a single topic.
In what order should I read them? Oldest first, starting at Day 1. The list above is newest first, so use the roadmap table if you want course order.
Is this free to read? Yes. Every post on GeekCoding101 is free to read and there is no sign-up.