Question

Consider a CNN that is made up of just one convolution layer consisting of just one filter F of shape 2 × 2 followed by a max-pooling layer of shape 2 × 2. The input image I is of shape 3 × 3. The output of the CNN is calculated as $\text{output} = \text{Pool}(\text{ReLU}(\text{Conv}(I)))$ where ReLU is the rectified linear activation function given by: $\text{ReLU}(x) = \text{max}(0, x)$ Also assume that the stride for the convolution and pool layers is 1 and no padding is applied. For the following values of the image I and weights of the filter F, compute the value of the output of the CNN: $\begin{pmatrix} 5 & 0 & 4 \\ 3 & 8 & 0 \\ 1 & 0 & 2 \end{pmatrix}$ $\begin{pmatrix} -2 & 0 \\ 0 & 3 \end{pmatrix}$

          Consider a CNN that is made up of just one convolution layer consisting of just one
filter F of shape 2 × 2 followed by a max-pooling layer of shape 2 × 2. The input
image I is of shape 3 × 3. The output of the CNN is calculated as
$\text{output} = \text{Pool}(\text{ReLU}(\text{Conv}(I)))$ 
where ReLU is the rectified linear activation function given by:
$\text{ReLU}(x) = \text{max}(0, x)$
Also assume that the stride for the convolution and pool layers is 1 and no padding
is applied.
For the following values of the image I and weights of the filter F, compute the value
of the output of the CNN:
$\begin{pmatrix} 5 & 0 & 4 \\ 3 & 8 & 0 \\ 1 & 0 & 2 \end{pmatrix}$ 
$\begin{pmatrix} -2 & 0 \\ 0 & 3 \end{pmatrix}$

Consider a CNN that is made up of just one convolution layer consisting of just one
filter F of shape 2 × 2 followed by a max-pooling layer of shape 2 × 2. The input
image I is of shape 3 × 3. The output of the CNN is calculated as
output = Pool(ReLU(Conv(I)))
where ReLU is the rectified linear activation function given by:
ReLU(x) = max(0, x)
Also assume that the stride for the convolution and pool layers is 1 and no padding
is applied.
For the following values of the image I and weights of the filter F, compute the value
of the output of the CNN:
< p m a t r i x >
< p m a t r i x >

Added by Ines G.

Question

Please give Ace some feedback