APPLICATION OF SUPERVISED LEARNING
DEEP LEARNING
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
|
|
(W-2P + F)/S + 1
|
|
|
(W + 2F-S)/P + 1
|
|
|
(W + 2P-F)/S + 1
|
|
|
(W + 2S-F)/P + 1
|
Detailed explanation-1: -The spatial dimensions(x, y) of a convolutional layer can be calculated as: (W in−F+2P)/S+1 .
Detailed explanation-2: -The output volume of the convolutional layer is obtained by stacking the activation maps of all filters along the depth dimension. Since the width and height of each filter is designed to be smaller than the input, each neuron in the activation map is only connected to a small local region of the input volume.
Detailed explanation-3: -Convolutional Layers In order to compute the pre-nonlinearity input to some unit xℓij in our layer, we need to sum up the contributions (weighted by the filter components) from the previous layer cells: xℓij=m−1∑a=0m−1∑b=0abyℓ−1(i+a)(j+b). Then, the convolutional layer applies its nonlinearity: yℓij=(xℓij).