Deep Learning Convolutional Neural Networks 1 — Questions and Answers
Question 1: What is the primary advantage of convolutional layers over fully connected layers for image data?
- Faster training on CPUs
- Parameter sharing and local connectivity reducing parameter count (Correct answer)
- Larger receptive fields per layer
- Elimination of activation functions
Correct answer: Parameter sharing and local connectivity reducing parameter count
Convolutional layers reuse the same filter weights across spatial positions, drastically reducing parameters while preserving spatial structure.
Question 2: What does a convolutional filter (kernel) do when applied to an input feature map?
- Performs element-wise addition
- Computes a dot product between the filter and a local patch of the input (Correct answer)
- Averages all pixel values globally
- Transposes the input matrix
Correct answer: Computes a dot product between the filter and a local patch of the input
A convolution filter slides over the input and computes the dot product between its weights and each local receptive field, producing an activation map.
Question 3: What is the purpose of pooling layers in a CNN?
- Increase spatial resolution
- Downsample feature maps to reduce computation and add spatial invariance (Correct answer)
- Apply non-linear activations
- Normalize feature map values
Correct answer: Downsample feature maps to reduce computation and add spatial invariance
Pooling layers reduce spatial dimensions by aggregating values in local regions, decreasing computation and making the representation more invariant to small translations.
Question 4: What does 'stride' refer to in a convolutional layer?
- The size of the convolutional filter
- The number of steps the filter moves per application (Correct answer)
- The number of output channels
- The padding added to input borders
Correct answer: The number of steps the filter moves per application
Stride controls how many pixels the filter shifts between consecutive applications, with larger strides producing smaller output feature maps.
Question 5: Which famous CNN architecture introduced residual (skip) connections to enable training of very deep networks?
- AlexNet
- VGGNet
- ResNet (Correct answer)
- Inception
Correct answer: ResNet
ResNet introduced shortcut connections that add the input directly to the output of a block, enabling gradients to flow unimpeded through hundreds of layers.
Question 6: What is the receptive field of a neuron in a CNN?
- The set of all neurons in the same layer
- The region of the input image that influences that neuron's activation (Correct answer)
- The number of filters in the layer
- The spatial size of the output feature map
Correct answer: The region of the input image that influences that neuron's activation
The receptive field defines which input pixels contribute to a given neuron's output, growing larger in deeper layers due to successive convolutions.
Deep Learning Convolutional Neural Networks 1
What is the primary advantage of convolutional layers over fully connected layers for image data?