5. What is the purpose of the softmax activation function?

To introduce non-linearity into the network

To output a probability distribution over multiple classes

To ensure that the output values of the network sum to one

All of the above

.

8. Which of the following is not a common type of layer used in a convolutional neural network?

a. Convolutional layer

b. Pooling layer

c. Dropout layer

d. Fully connected layer

.

9. Which of the following is the dimension of the feature maps produced by applying a convolutional operation with 32 filters and a kernel size of 3 on an input image with dimension 224x224x3, using no padding and a stride of 1?

a. 222x222x32

b.222x222x3

c. 222x222x96

d. 222x222x1

.

10. What is the dimension of the feature maps produced by applying max pooling on input feature maps with dimension 112x112x64, using a filter size of 2 and stride of 2 and no padding?

a. 56x56x64

b. 56x56x32

c. 112x112x32

d. 224x224x64