Lessons
The overview is the whole idea in one sitting. These pages take one concrete case each and walk it through end to end — inputs, steps, and result — so you can see how the vocabulary from Terms shows up in practice.
Machine Learning
How a model improves from examples: labels, features, training, and the difference between fitting data and predicting on new data.
- 01
Your First Learning Model
One feature, one weight, and a training loop that discovers dollars per square foot from a sold house.
- 02
Vectors and Weights
Pack sqft, bedrooms, and age into a feature vector, pair it with one weight per feature, and predict with a dot product.
- 03
Linear Regression
Train a linear model with weights and bias on all five houses, watch MSE fall, then predict a new listing.
- 04
Gradient Descent
Walk downhill on error: one weight on a loss bowl, then the same step on every knob — with a learning-rate dial.
- 05
A Single Neuron
Add ReLU to the weighted sum you already know — one neuron that can bend, and why XOR still needs a network.
- 06
Neural Networks
Stack layers, run a forward pass, send blame backward — train XOR with hidden ReLU neurons and a linear output.
- 07
Price Tier Classifier
Turn HOUSES into cheap / mid / expensive with softmax — classification instead of a dollar amount.
- 08
Generalization
Hold out a house, watch train vs held-out error, and name overfitting — why train loss alone is not success.
Related concepts
| Topic | Description |
|---|---|
| Artificial Intelligence (AI) | What AI is at the first layer: human decisions turned into computer rules — before machine learning enters the picture. |
| Deep Learning | Machine learning with stacked neurons and ReLU layers: how a deep network builds a price guess from house features in TypeScript. |