Font size
WorksheetsWeek4_S2
Total questions: 10
Worksheet time: 5mins
Max pooling with a 2x2 window and stride 2 reduces the output size by:
Half in each dimension
Quarter in each dimension
No change in size
One-third in each dimension
The output produced by applying a filter to an image is called a (a) map.
To prevent overfitting, pooling layers reduce the number of (a) in the network.
What is the main role of pooling layers in a CNN?
Decrease model complexity
Downsample feature maps
Add more parameters to the network
Improve filter weights directly
Which of the following combinations will most likely lead to overfitting in a CNN?
Small filters + pooling + dropout
Large filters + small dataset + no regularization
Many small filters + large dataset
High learning rate + regularization
The Flatten() layer is used to:
Normalize pixel values
Reduce the number of features
Convert feature maps into a vector
Increase batch size
Increasing the number of convolutional filters primarily:
Reduces model complexity
Replaces pooling layers
Reduces computation time
Increases model’s feature extraction capacity
Zero-padding is often used to:
Reduce overfitting
Increase the input image dimension
Randomly remove neurons
Preserve feature map dimensions
Which activation function is most commonly used in modern CNNs for hidden layers?
Sigmoid
ReLU
Tanh
Softmax
(a) pooling keeps the maximum value from each region of the input.
