Learn AIHow does a network learn?
Start with a single neuron. Discover how small numerical steps become learning.
What you’ll explore
- Neurons & predictions
- Loss & gradient descent
- Hidden layers
- Backpropagation
Your lessons
0 / 12 completeYour first neuron
Turn inputs, a weight, and a bias into a prediction.
Follow the slope of a mistake
Turn errors into a loss curve, then find out why the size of a learning step matters.
Make a problem easier to see
Build XOR with two hidden neurons and discover what nonlinear activations add.
Send the error backward
Trace a mistake through two weights, calculate both gradients, and then update them together.
Learn from small batches
Inspect individual gradient arrows, average a mini-batch and compare learning under explicit example and update budgets.
Use momentum and adaptive steps
Compare gradient descent, accumulated momentum and Adam while inspecting their state and actual parameter changes.
Schedule the learning rate
Compare warmup, step decay and cosine decay, then choose a checkpoint using declared development checks and stopping rules.
Initialize and normalize
Inspect activation and gradient scales, break hidden-unit symmetry, and compare batch and layer normalization in training and evaluation modes.
Trace disappearing and exploding gradients
Follow exact derivatives through depth and time, compare identity residual paths and inspect globally clipped parameter updates.
Make numerical computation trustworthy
Break naive softmax, repair its log-domain loss and check gradients with explicit perturbation sizes and tolerances.
Choose complexity using development evidence
Compare model capacity, weight penalties, dropout and training duration using saved classifier candidates before opening the test set.
Compare manual and automatic gradients
Build a small computation graph, inspect each backward contribution and compare automatic gradients with manual formulas and finite differences.