All tracksStart here 30 60 200
Deep Learning Challenges
Learn the idea, implement the important part, then prove you can use it.
Your challenge path
0/3
Challenges complete · progress is saved in this browser
The curriculum
Build the skill one module at a time.
The first two levels are untimed. Later challenges add pressure only after the workflow feels familiar.
Module 1
Neural Network Foundations
activation functions · gradients
Choose your difficulty
All levels
Browse the full module path
Guided
ReLU + derivative
Implement `relu(x)` and `relu_grad(x)` for a scalar input.
No timerOpen
Supported
Sigmoid + numerical gradient
Implement `sigmoid(x)` and verify its gradient equals sigmoid(x)*(1-sigmoid(x)).
No timerOpen
Interview
Backprop a 2-layer net
Implement forward + backward for a 2-layer MLP and learn XOR to zero error. No frameworks.
Timed when startedOpen
Understand the idea first. Then make the code yours.