Playgrounds
Machine learning you can operate. Every lab makes one normally-invisible idea visible, lets you change it, and shows the consequence immediately — including what happens when you push it until it breaks.
34 of 34 labs are ready to run. The rest are planned.
Foundations
2Bias-Variance Tradeoff
How model complexity drives a tradeoff between capturing the underlying signal (bias) and overreacting to noise (variance).
5 stages
Train/Test Split & CV
How data partitioning works: splitting testing data out prevents overfitting, while cross validation allows for model evaluation across the entire training set robustly.
4 stages
Supervised Learning
8Gradient Descent
How a model actually learns: it measures how wrong it is, works out which way to move each parameter to be less wrong, and takes a small step that way.
7 stages
k-Nearest Neighbors
This model has no equation and learns nothing at training time. Its decision boundary is an emergent shape, produced entirely by asking which labelled points are nearest.
3 stages
Naive Bayes Classifier
How Bayes' rule updates prior beliefs incrementally as independent pieces of evidence (features) are multiplied in.
4 stages
Decision Trees
how a model uses simple axis-aligned splits to isolate classes by reducing impurity.
4 stages
Logistic Regression & Decision Boundaries
A decision boundary is not an intrinsic property of the model; it is just a chosen threshold on top of a continuous probability surface.
3 stages
Supervised Ensembles: Random Forests & Boosting
How multiple simple decision trees can collaborate to model complex boundaries without overfitting, and how boosting forces focus on difficult examples.
5 stages
Support Vector Machines
You are seeing the margin boundaries and the hidden higher-dimensional space where a simple flat plane can separate complex patterns.
4 stages
Ridge & Lasso Regularization
How a penalty term shrinks model coefficients and differentially selects features (Lasso) vs shrinking them together (Ridge).
3 stages
Unsupervised Learning
2K-Means Clustering
Clustering without labels is a loop of two operations that each improve one thing while holding the other fixed — and it always converges, whether or not it converged to anything sensible.
3 stages
Principal Component Analysis (PCA)
how PCA finds the direction of maximum variance to reduce dimensionality while preserving information
4 stages
Neural Networks
6Convolution / CNN
How a convolutional kernel slides over an image to compute a dot product at each step, building an output feature map cell by cell.
4 stages
Perceptron & Activation Functions
A neuron is a weighted sum followed by one squashing function — and the slope of that function, not the function itself, is what decides whether learning can happen at all.
5 stages
Backpropagation
How the chain rule assigns "blame" for errors to individual weights across multiple layers.
7 stages
Batch Norm & Dropout
how regularization and normalization stabilize training and prevent overfitting by bounding activations and forcing redundancy.
3 stages
Multi-Layer Perceptron
How hidden layers and non-linear activations warp the feature space to separate complex data that a single line cannot.
4 stages
RNN vs LSTM Memory
Standard RNNs lose earlier information because gradients vanish when multiplied repeatedly over time. LSTMs preserve information through explicit memory gates and a separate cell state.
5 stages
Modern ML
2Attention
Attention is not a metaphor. It is a matrix of real numbers saying how much each token reads from each other token, and every row of it sums to exactly one.
4 stages
Transformer Decoding
Generation strategies manipulate an underlying probability distribution before the next token is sampled.
4 stages
Generative AI
8Embeddings & Vector Space
Words as points in high-dimensional space where distance means semantic similarity and directions carry conceptual meaning.
4 stages
Diffusion Models
Generation as an iterative denoising process rather than a one-shot creation.
4 stages
Generative Adversarial Networks (GANs)
how two networks improve each other by competing, with the discriminator grading realism and the generator learning to fool it.
5 stages
Autoencoder / VAE
how an autoencoder compresses data into a lower-dimensional latent space and reconstructs it
3 stages
Full Transformer Block
how a single transformer block processes tokens through multi-head attention and a feed-forward network with residual connections
5 stages
LoRA (Low-Rank Adaptation)
How decomposing a massive weight update into two low-rank matrices drastically reduces trainable parameters while maintaining learning capability.
4 stages
Retrieval-Augmented Generation (RAG)
How a model augments its parametric memory with an external knowledge base by embedding a query, matching it against document embeddings, and injecting the nearest context into its prompt before generation.
4 stages
Tokenization (BPE)
How models see text as statistically common subword chunks formed by merging frequent character pairs.
2 stages
Evaluation & RL
4Q-Learning
How an agent learns the value of state-action pairs (Q-values) through trial, error, and delayed rewards in an environment.
3 stages
Threshold, Confusion Matrix & ROC
A classifier does not output a class. It outputs a score, and someone chooses where to cut — so accuracy, precision and recall are properties of that choice rather than of the model.
3 stages
Policy Gradient
How an agent optimizes its policy probabilities directly based on rewards, rather than estimating Q-values for each state-action pair.
3 stages
Precision-Recall Curve
ROC curves reward models for correctly rejecting the abundant negative class, hiding poor performance on the rare positive class. Precision-Recall curves focus only on what matters: the positives.
3 stages
Optimizers
2Advanced Optimizers
Modern optimizers adapt by remembering past gradients (Momentum) or scaling step sizes (RMSProp), rather than just reacting to the local slope like SGD.
4 stages
Learning Rate Scheduling
how modifying the learning rate over time affects the optimizer's convergence speed and stability
4 stages