Mixed Deck — All CNN Topics Flashcards

Which of the following classic CNN architectures was the first to successfully demonstrate that significantly deeper networks could be trained by using 'skip connections' or 'residual blocks' to address the vanishing gradient problem?

Answer: ResNet

ResNet (Residual Network) introduced the concept of residual blocks with skip connections. These connections create a shortcut path for the gradient to flow through, which helps mitigate the vanishing gradient problem that plagues very deep networks. This innovation allowed for the successful training of networks that were substantially deeper (e.g., 50, 101, or 152 layers) than previous architectures like AlexNet or VGG.

What filter size does VGGNet use exclusively in its convolutional layers?

Answer: 3x3

VGGNet uses only 3x3 convolutional filters, showing that stacking small filters achieves the same receptive field as larger filters with fewer parameters.

How does a transposed convolution (sometimes called deconvolution) differ from a standard convolution in terms of spatial output?

Answer: It increases spatial dimensions, making it useful for upsampling

Transposed convolution is the gradient operation of a forward convolution; it increases spatial size and is used in decoders, GANs, and segmentation networks.

The gradient of a substance's concentration, such as urea, during peritoneal dialysis

Answer: Decreases

During peritoneal dialysis, the dialysate solution is introduced into the peritoneal cavity, creating a concentration gradient for waste products like urea. Initially, urea concentration is high in the blood and low in the dialysate. As dialysis progresses, urea moves from the blood into the dialysate, causing its concentration in the blood to decrease and its concentration in the dialysate to increase, thus reducing the overall concentration gradient over time until equilibrium is approached.

A data scientist is designing a CNN to classify high-resolution medical images. They are concerned about losing important information at the borders of the images during the convolution operations. Which technique should they employ to mitigate this issue?

Answer: Adding a padding layer around the input images.

Padding involves adding extra pixels (usually zeros) around the border of an input image. This technique ensures that the filter can process the pixels at the edges of the image more effectively, preventing the spatial dimensions from shrinking with each convolution and preserving information at the borders.

One hemodialysis patient may respond to difficulty with little outward stress and cope well. In contrast, another, like Mike Smith, may react to the same issue with intense tension and worry and have difficulty coping. This could be due to the individuals' different coping mechanisms.

Answer: Resilience

Resilience refers to an individual's ability to adapt well and recover quickly from difficulties, stress, or adversity. The scenario describes two individuals reacting differently to the same issue, with one coping well and the other struggling, which directly illustrates varying levels of resilience in their coping mechanisms. It encompasses the capacity to bounce back from challenging experiences.

The VGGNet architecture is renowned for its simplicity and depth. What is the defining characteristic of its convolutional layers?

Answer: It exclusively uses very small 3x3 filters stacked on top of each other.

The key innovation and defining feature of the VGG architecture is its uniformity and simplicity, achieved by exclusively using small 3x3 convolutional filters stacked to increase the network's depth. This approach increases the effective receptive field and allows for learning more complex features with more non-linearities, while keeping the number of parameters manageable.

Which of the following activation functions would be most appropriate for the output layer of a CNN designed for a multi-class classification problem (e.g., classifying images into 10 different categories)?

Answer: Softmax

The Softmax function is ideal for multi-class classification because it converts a vector of raw output scores (logits) into a probability distribution over the classes. Each output value is between 0 and 1, and the sum of all output values equals 1, representing the model's confidence for each class.

What are dilated (atrous) convolutions and why are they used in semantic segmentation?

Answer: Convolutions with gaps between kernel elements that expand the receptive field without increasing parameters or losing resolution

Dilated convolutions insert zeros between kernel weights (dilation rate > 1), allowing the filter to cover a larger area of the input without downsampling, which is critical for maintaining spatial resolution in segmentation.

Which layer type in a CNN is responsible for introducing non-linearity?

Answer: Activation layer

Activation layers (e.g., applying ReLU) introduce non-linearity after convolution, enabling the network to learn complex patterns.

What is 'negative transfer' in the context of transfer learning with CNNs?

Answer: When pretraining hurts performance on the target task

Negative transfer occurs when features from the source domain are incompatible with the target domain, degrading target task performance.

In a CNN, what does 'stride' control?

Answer: How many pixels the filter moves between applications

Stride determines the step size of the filter as it slides across the input, with larger strides producing smaller output feature maps.

Which layer type is typically removed when adapting a pretrained CNN for a new classification task?

Answer: Fully connected output layer

The final fully connected (classification) layer is replaced because it was trained for the original task's class labels.

In the Feature Pyramid Network (FPN), how are features from different levels combined?

Answer: By top-down pathway with lateral connections

FPN uses a top-down pathway that upsamples high-level features and adds them to lower-level features via lateral connections.

Despite the adverse bodily reaction, Mike Smith has recently started skipping treatments and refusing to take recommended drugs. When questioned, the patient smiles and says he is alright but was "busy" and "forgot" about the treatments. The nurse should think about

Answer: Suicidal ideation

In a patient with chronic illness and depression, non-adherence to life-sustaining treatments and medication, coupled with a dismissive attitude, can be a significant indicator of suicidal ideation. This behavior might signal a passive desire to end life or a lack of will to live, rather than simple forgetfulness. Nurses should prioritize assessing for suicidal thoughts in such situations to ensure patient safety.

Which regularization technique randomly zeroes out feature maps during training in CNNs rather than individual neurons?

Answer: Spatial Dropout

Spatial Dropout drops entire feature maps (channels) instead of individual activations, which is more effective for spatially correlated CNN features.

In a CNN, a 4×4 feature map with a 2×2 max pooling kernel and stride 2 produces an output of what size?

Answer: 2×2

With a 2×2 kernel and stride 2, each dimension is halved: (4-2)/2 + 1 = 2, so the output is 2×2.

What does the mean Intersection over Union (mIoU) metric measure in semantic segmentation evaluation?

Answer: The average of per-class IoU scores, where IoU measures overlap between predicted and ground-truth masks

mIoU computes IoU (intersection divided by union of predicted and ground-truth regions) for each class and averages them, providing a balanced measure across all classes including rare ones.

The LeNet-5 architecture, a pioneering CNN, was primarily designed for a specific task and had characteristic features for its time. Which of the following best describes LeNet-5?

Answer: A shallow network using average pooling and tanh/sigmoid activations, designed for handwritten digit recognition.

LeNet-5, developed by Yann LeCun, was a foundational 7-layer CNN designed for handwritten digit recognition on the MNIST dataset. Its architecture was characterized by its relatively shallow depth, alternating convolutional and average pooling layers, and the use of sigmoid or tanh activation functions.

What is Panoptic Segmentation?

Answer: A unified task that combines semantic segmentation (stuff) and instance segmentation (things) into a single cohesive map

Panoptic segmentation assigns each pixel both a semantic class label and an instance ID where applicable, unifying the 'stuff' categories of semantic segmentation with the 'things' categories of instance segmentation.