BeginnerCoder
Donate
AI / ML Foundations course cover

AI / ML Foundations

The math and Python behind machine learning — run it yourself.

1
Lesson 1 — Data as numbers
basics · 7 min
→2
Lesson 2 — Normalisation
easy · 9 min
→3
Lesson 3 — Similarity
medium · 10 min
→4
Lesson 4 — Prediction by average
medium · 10 min
→5
Lesson 5 — The sigmoid
medium · 10 min
→6
Lesson 6 — Sigmoid: choosing a threshold
medium · 9 min
→7
Lesson 7 — Scaling new data with training stats
medium · 9 min
→8
Lesson 8 — One-hot encoding
medium · 10 min
→9
Lesson 9 — Dot product & norm
medium · 9 min
→10
Lesson 10 — Standardize features
medium · 9 min
→11
Lesson 11 — A tiny training step
hard · 13 min
→12
Lesson 12 — Accuracy
hard · 10 min
→13
Lesson 13 — Train / test split
hard · 11 min
→14
Lesson 14 — Mean squared error
hard · 10 min
→15
Lesson 15 — Cosine similarity
hard · 12 min
→16
Lesson 16 — k-NN (tiny)
hard · 13 min
→17
Lesson 17 — Confusion counts
hard · 11 min
→18
Lesson 18 — Gradient over a whole dataset
hard · 12 min
→19
Lesson 19 — Linear regression (closed form)
hard · 12 min
→20
Lesson 20 — Gradient descent
hard · 13 min
→21
Lesson 21 — Logistic prediction
hard · 12 min
→22
Lesson 22 — k-means step (expert)
hard · 13 min
→23
Lesson 23 — Gradient descent with early stopping
very hard · 15 min
→24
Lesson 24 — Logistic regression training
very hard · 15 min
→25
Lesson 25 — Ultimate: tiny neural net
★ ultimate · 15 min
→