Deep Learning Foundations
What a neural network actually computes, how the chain rule delivers every gradient in one backward sweep, and why convolution is the right prior for an image.
Intermediate400 XP~2 h90% to advance
Sign in to take quizzes, earn XP, and unlock stages as you reach 90% mastery.
What a Network Computes
30 min · 120 XPLayers as parameterised functions, the affine-then-nonlinearity pattern, and why stacking linear maps alone buys you nothing.
Open lesson →Sign in to take the 3-question quiz.
Backpropagation in Practice
40 min · 160 XPOne forward pass, one backward pass, and every gradient in the network - worked end to end on a two-layer example with real numbers.
Open lesson →Sign in to take the 4-question quiz.
Convolution as a Prior
30 min · 120 XPWhy a dense layer is the wrong tool for pixels, and what weight sharing and locality actually assume about images.
Open lesson →Sign in to take the 3-question quiz.
Key concepts
Complete all modules → earn the Deep Learning Foundations badge