Login to unlock
Deep Learning · Phase 2: Forward & Backward Propagation · Forward Propagation

Forward Propagation — Checkpoint Quiz

Checkpoint quiz 3 questions
Back to course

Check your understanding of this module before moving on.

?

Checkpoint quiz 3 questions

A quick check on this module's key ideas before you move on
0/3
Question 01

In forward propagation, what does each layer pass to the next?

B is correct. Forward propagation is a chain: each layer takes the previous layer's output activations, applies its own weighted sum and activation function, and passes the result onward.
Question 02

Why is it useful to think of a multi-layer network as a composition of functions, f3(f2(f1(x)))?

B is correct. Once you see the network as nested functions, computing how the final loss changes with respect to early-layer weights is exactly the chain rule from calculus applied across each nested function.
Question 03

If a network's weight matrix for a layer has shape (64, 128), what does this tell you about that layer?

A is correct. By convention, a weight matrix mapping an input of size 128 to an output of size 64 has shape (64, 128), since each of the 64 output neurons has its own row of 128 weights to dot with the input.