QUIZ CNN

What is the primary purpose of the convolutional layer in a CNN?

• Reducing dimensionality

• Feature extraction

• Non-linearity

• Classification

What is the role of pooling layers in CNNs?

• Reducing spatial dimensions

• Increasing feature maps

• Introducing non-linearity

• Feature extraction

What is the purpose of the term 'padding' in convolutional layers?

• Increase computational efficiency

• Reduce the size of the feature maps

• Enhance the performance of pooling layers

• Prevent loss of information at the borders

What is the 'kernel' in a CNN?

• A type of layer

• A weight matrix used in convolution

• A pooling filter

• The output of a convolutional layer

In transfer learning with CNNs, what are the 'pre-trained' weights?

• Weights learned during the current training session

• Weights obtained from a previous model trained on a different task

• Randomly initialized weights

• Weights initialized with zeros

In CNNs, what is the purpose of the softmax activation function in the output layer?

• Introduce non-linearity

• Control learning rate

• Normalize the output into probability scores

• Stabilize gradients

Which of the following statements about Convolutional Neural Networks (CNNs) is incorrect?

• Pooling layers are typically used in CNNs to reduce the spatial dimensions of the input volume.

• The weights in the convolutional layers of a CNN are shared across different spatial locations.

• Stride in a convolutional layer determines the number of filters applied to the input.

• In transfer learning with CNNs, fine-tuning involves training only the fully connected layers while keeping the convolutional layers frozen.

• Batch Normalization is commonly used in CNNs to accelerate training and improve generalization.

In a CNN, what does the term 'depth' refer to in the context of convolutional layers?

• The number of input channels

• The number of filters in a layer

• The size of the kernel

• The number of strides applied