Your question is ANN vs CNN and Gradient Descent. 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 the difference between an ANN and a CNN, and then explain gradient descent.
Contrast their architectures, suitable input types, parameter sharing, and inductive biases. Explain forward propagation, loss computation, backpropagation, learning rate, and parameter updates, then demonstrate the concepts with a small implementation.