Question 7: Consider a hidden layer with neurons, all initialized wit…

Select all that apply.

1. A

   After one gradient descent step, the neurons will have different weights.

2. B

   For any input , all neurons will produce the same output.

3. C

   During backpropagation, the gradients of all neurons are always zero because their weights are identical.

4. D

   This layer is functionally equivalent to having a single neuron, because all neurons compute the same function.