Objective: understand how a final error becomes a local correction.
The gradient gathers the derivatives of the loss with respect to the
parameters. Its component ∂L/∂w_i indicates how a small increase in weight
w_i would affect the loss.
If L depends on a, which depends on z, which depends on w:
∂L/∂w = ∂L/∂a × ∂a/∂z × ∂z/∂wBackpropagation applies this rule efficiently from the loss down to every parameter of the graph. It is not the optimizer: it computes the gradients; the optimizer then decides the update.
optimizer.zero_grad() # clear previous gradients
logits = model(x)
loss = criterion(logits, y)
loss.backward() # compute gradients
optimizer.step() # update parametersPreview — the rest of the lesson is for enrolled readers.
Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.
Sign inNo account yet? Create oneThe first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.