# Learn AI from the ground up

How simple rules can create complex behavior

Meet the simplest model of computation and see how a machine with almost no memory, no intuition, and only a few rules can still perform meaningful work.

20 min

How AI talks about uncertainty

Build intuition for uncertainty, common distributions, and belief updates so predictions feel measurable rather than hand-wavy.

25 min

How computers find good routes

See how a search algorithm compares routes, updates costs, and reliably finds a strong path through a network of choices.

20 min

From examples to predictions

Get clear on what it means to train on data, what a model actually learns, and why different problems require different learning setups.

20 min

Predicting numbers and choosing categories

Understand the two most common prediction jobs in machine learning: estimating a value and assigning a label.

30 min

Learning by asking better questions

See how a model learns a sequence of split decisions, and why combining many trees often generalizes better than trusting a single one.

25 min

Finding the safest separating line

Learn how SVMs separate classes by choosing a boundary that maximizes the margin rather than merely drawing any line that works.

25 min

Finding groups without labels

Explore how K-means groups unlabeled data by repeatedly assigning points to centers and then moving those centers to better represent the data.

20 min

Keeping the important information

Learn why too many features can blur patterns, and how dimensionality reduction creates simpler views that preserve much of the useful structure.

25 min

Cleaning, scaling, encoding, and splitting

Before any model can learn, the data needs a thorough clean-up. Here we learn how to wash, organize, and portion our data like a chef prepping ingredients.

30 min

Selecting, creating, and guarding your inputs

The art of choosing and crafting the right inputs so a model sees the signal, not the noise.

30 min

Distributions, Bayes, and hypothesis testing

Go deeper into the statistical toolkit every ML practitioner reaches for: distributions, Bayes' rule, and the logic of hypothesis testing.

35 min

Gradient descent, learning rate, and loss functions

Meet the engine that powers every learning algorithm: gradient descent. We follow a model as it slides downhill toward better answers, one careful step at a time.

30 min

Overfitting, underfitting, and regularization

Every model walks a tightrope between memorizing the training data and failing to learn enough. Here we learn to spot the fall and catch it with regularization.

30 min

Accuracy, precision, recall, F1, and ROC-AUC

Accuracy alone can lie. Here we learn the full scorecard—precision, recall, F1, confusion matrices, and ROC curves—so we can measure what truly matters.

30 min

Baselines, ablations, and reproducibility

Science demands proof, not just results. Learn to run experiments that are fair, repeatable, and actually convincing.

25 min

Feature importance, SHAP, and LIME

A prediction is only useful if you can explain why. Learn to open the black box and show stakeholders what drove each decision.

30 min

Bias, privacy, and responsible use

AI reflects the data and choices we feed it. Here we confront bias, respect privacy, and discuss what it means to deploy AI responsibly.

30 min

Serving, monitoring, and drift

A model in a notebook helps no one. Learn how models reach real users—and what can go wrong once they do.

25 min

From neurons to layered predictions

See how layers, weights, biases, and activations combine to transform raw inputs into a usable prediction.

35 min

How a network learns from mistakes

Follow how a network measures its mistakes, sends error information backward, and updates its weights to improve over time.

30 min

How models learn to see images

Discover how convolutional layers slide filters across images to detect edges, shapes, and objects — the architecture behind modern computer vision.

30 min

When the real state is hidden from view

Learn how observable clues can be used to infer hidden states and recover the most likely explanation underneath a sequence.

30 min

Neural networks with memory

See how recurrent models carry context forward through time, and how LSTMs improve that memory when long sequences start to strain basic RNNs.

30 min

How words become meaningful vectors

Learn how language models map words into vectors so similarity, context, and analogy can be represented numerically.

25 min

How models decide what to focus on

See how attention lets each token pull in the context it needs, making long-range relationships easier to capture than in older sequence models.

35 min

Predicting the next token at scale

Understand how transformer models trained on massive corpora learn to generate text one token at a time and why that process can produce both impressive and unreliable behavior.

30 min

Learning by trying, failing, and improving

Watch an agent learn through trial, reward, and delayed consequences rather than from labeled examples with fixed answers.

30 min

Training together without sharing raw data

Explore how many devices or institutions can improve a shared model together while keeping raw local data where it was collected.

25 min