Your question is Backpropagation Explanation. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
Explain backpropagation and how gradients flow through a neural network.
Describe the forward pass, loss calculation, chain rule, reverse-mode differentiation, and parameter updates. Demonstrate the explanation with a small neural-network implementation and verify at least one analytical gradient against a numerical finite-difference estimate.