a) Output should be flattened before feeding it to a fully connected layer b) There can be only 1 fully connected layer in CNN c) We can use as many convolutional layers in CNN d) None of the above
2) The input image has been converted into a matrix of size 64 × 64 and a kernel of size 5 × 5 with a stride of 1 and no padding. What will be the size of the convoluted matrix?
a) 5 × 5 b) 59 × 59 c) 60 × 60 d) None of the above
3) A filter size of 3 × 3 is convolved with a matrix of size 4 × 4 (stride = 1). What will be the size of the output matrix if valid padding is applied?
4) Let us consider a Convolutional Neural Network having three different convolutional layers in its architecture as:
Layer-1: Filter Size 3 × 3, Number of Filters 10, Stride 1, Padding 0
Layer-2: Filter Size 5 × 5, Number of Filters 20, Stride 2, Padding 0
Layer-3: Filter Size 5 × 5, Number of Filters 40, Stride 2, Padding 0
Layer 3 of the above network is followed by a fully connected layer. If we give a 3D image input of dimension 39 × 39 to the network, then which of the following is the input dimension of the fully connected layer?
5) Suppose you have 40 convolutional kernels of size 3 × 3 with no padding and stride 1 in the first layer of a convolutional neural network. You pass an input of dimension 1024 × 1024 × 3 through this layer. What are the dimensions of the data which the next layer will receive?
a) 1020 × 1020 × 40 b) 1022 × 1022 × 40 c) 1022 × 1022 × 3 d) None of the above
6) Consider a CNN model which aims at classifying an image as either a rose, a marigold, a lily, or an orchid (consider the test image can have only one of the classes at a time). The last (fully-connected) layer of the CNN outputs a vector of logits, L, that is passed through an activation function that transforms the logits into probabilities, P. These probabilities are the model predictions for each of the 4 classes. Fill in the blanks with the appropriate option.
7) Suppose your input is a 300 × 300 color (RGB) image, and you use a convolutional layer with 100 filters that are each 5 × 5. How many parameters does this hidden layer have (without bias)?
9) Statement 1: Residual networks can be a solution for the vanishing gradient problem. Statement 2: Residual networks provide residual connections straight to earlier layers. Statement 3: Residual networks can never be a solution for the vanishing gradient problem.
Which of the following options is correct?
a) Statement 2 is correct b) Statement 3 is correct c) Both Statement 1 and Statement 2 are correct d) Both Statement 2 and Statement 3 are correct
