19
(Choose 1 answer)
In lecture we talked about "sparsity of connections" as a benefit of using convolutional layers. What does this mean?
A. Each filter is connected to every channel in the previous layer.
B. Each activation in the next layer depends on only a small number of activations from the previous layer.
C. Each layer in a convolutional network is connected only to two other layers.
D. Regularization causes gradient descent to set many of the parameters to zero.
