Certified Nephrology Nurse Exam — Questions and Answers

Question 1: A CNN model's training loss is decreasing very slowly, and the model seems to be stuck. To accelerate convergence, the data scientist decides to switch from standard SGD to an adaptive learning rate optimizer. Which optimizer combines the benefits of both momentum and adaptive learning rates by keeping track of exponentially decaying averages of past gradients and past squared gradients?

Adam (Correct answer)
Nesterov Accelerated Gradient
RMSprop
Adagrad

Correct answer: Adam

The Adam optimizer, which stands for Adaptive Moment Estimation, computes adaptive learning rates for each parameter. It stores an exponentially decaying average of past squared gradients like RMSprop, and it also keeps an exponentially decaying average of past gradients, which is similar to momentum. [32, 35] This combination often leads to faster convergence than other optimizers like standard SGD or even RMSprop alone. [34]

Question 2: What does the ColorJitter augmentation randomly alter in a training image?

Brightness, contrast, saturation, and hue (Correct answer)
Aspect ratio
Image resolution
Image geometry

Correct answer: Brightness, contrast, saturation, and hue

ColorJitter randomly perturbs brightness, contrast, saturation, and hue to make models robust to varying lighting and color conditions.

Question 3: What distinguishes a 'same' padding strategy from a 'valid' padding strategy in convolutional layers?

Same padding uses larger filters; valid padding uses 1×1 filters
Same padding pads the input so output spatial size equals input size; valid padding applies no padding, shrinking output (Correct answer)
Same padding is only used in pooling; valid padding applies to convolutions
Same padding doubles the input size; valid padding halves it

Correct answer: Same padding pads the input so output spatial size equals input size; valid padding applies no padding, shrinking output

With 'same' padding, zeros are added so the output matches the input's spatial dimensions; with 'valid', no padding is added and the output shrinks based on filter size.

Question 4: A machine learning engineer is tasked with classifying rare mineral types from a very small and highly specialized dataset of microscopic images (fewer than 500 samples). This domain is visually very different from ImageNet. Which of the following describes the most significant challenge when applying transfer learning with a standard ImageNet pre-trained model?

The high-level features learned from ImageNet (e.g., 'cat fur', 'car tire') are unlikely to be relevant to microscopic mineral textures, and fine-tuning risks severe overfitting on the tiny dataset. (Correct answer)
The pre-trained CNN architecture, like ResNet, will be computationally too simple to capture the complexity of the new features.
The model will converge too quickly on the small dataset, leading to a suboptimal but highly generalized solution.
It will be impossible to replace the final layer of the pre-trained model due to architectural constraints.

Correct answer: The high-level features learned from ImageNet (e.g., 'cat fur', 'car tire') are unlikely to be relevant to microscopic mineral textures, and fine-tuning risks severe overfitting on the tiny dataset.

This scenario represents the most difficult case for transfer learning: a small dataset that is very different from the source domain. The high-level, abstract features learned by the later layers of the ImageNet model are not transferable to the new domain. Attempting to fine-tune these layers on such a small dataset would likely cause the model to memorize the few examples it has, resulting in poor generalization (overfitting).

Question 5: Which Python library function is commonly used to extract intermediate layer outputs for feature map visualization in Keras?

Model(inputs, intermediate_layer.output) (Correct answer)
layer.get_weights()
model.predict()
keras.backend.function()

Correct answer: Model(inputs, intermediate_layer.output)

Creating a new Keras Model with the original input and an intermediate layer's output allows you to forward-pass an image and retrieve that layer's activations.

Question 6: Which pooling operation is most commonly used in CNNs and what does it compute?

L2 pooling — computes the Euclidean norm of values in the window
Max pooling — selects the maximum value in the pooling window (Correct answer)
Average pooling — computes the mean of values in the pooling window
Stochastic pooling — randomly samples a value weighted by activation magnitude

Correct answer: Max pooling — selects the maximum value in the pooling window

Max pooling takes the largest activation within each region, retaining the strongest feature response and providing a degree of translation invariance.

Question 7: What is the receptive field of a neuron in a CNN?

The output size of the layer it belongs to
The number of channels it processes
The region of the input image that influences that neuron's activation (Correct answer)
The set of weights in its corresponding filter

Correct answer: The region of the input image that influences that neuron's activation

The receptive field is the spatial extent of the original input that a given neuron 'sees', which grows with depth due to successive convolutions.

Question 8: Where is batch normalization typically inserted in a convolutional block?

Before the activation function, after the convolutional layer (Correct answer)
Between the pooling layer and the fully connected layer only
After the activation function, before the pooling layer
Before the convolutional layer, after the pooling layer

Correct answer: Before the activation function, after the convolutional layer

Batch normalization is typically applied after the convolutional operation and before the activation function (e.g., Conv → BN → ReLU) to normalize pre-activation values.

Question 9: What is a known limitation of batch normalization when using very small batch sizes?

Batch statistics become noisy and unreliable, degrading performance (Correct answer)
It cannot be used with convolutional layers, only fully connected layers
The running mean is reset to zero after each batch
Learnable parameters gamma and beta become unstable

Correct answer: Batch statistics become noisy and unreliable, degrading performance

With very small batch sizes (e.g., 1 or 2 samples), the per-batch mean and variance estimates are too noisy to be useful, making batch normalization less effective.

Question 10: What is the key difference between a standard convolution operation and a transposed convolution (often called deconvolution)?

Standard convolution is used for up-sampling, while transposed convolution is for down-sampling.
Transposed convolution is a mathematical operation that performs learnable up-sampling, increasing the spatial resolution of the feature map. (Correct answer)
They are identical operations but are used in different parts of the network.
Transposed convolution does not use learnable filters.

Correct answer: Transposed convolution is a mathematical operation that performs learnable up-sampling, increasing the spatial resolution of the feature map.

While a standard convolution typically reduces spatial dimensions, a transposed convolution works to increase them. It is not the mathematical inverse of convolution but is mechanically the backward pass of a standard convolution, allowing the network to learn how to up-sample feature maps, which is crucial in tasks like semantic segmentation and image generation.

Question 11: What is the 'Random Erasing' augmentation technique?

Removing random images from the dataset
Erasing random weight connections
Randomly selecting a rectangle in the image and replacing it with random pixel values (Correct answer)
Erasing random layers from the network

Correct answer: Randomly selecting a rectangle in the image and replacing it with random pixel values

Random Erasing selects a random rectangular region in the training image and replaces it with random noise or a constant value, helping the model become robust to partial occlusion.

Question 12: In a convolutional layer, what is the effect of increasing the stride value from 1 to 2?

It requires the use of 'valid' padding.
It reduces the spatial dimensions of the output feature map. (Correct answer)
It increases the number of parameters in the model.
It enhances the detection of fine-grained, detailed features.

Correct answer: It reduces the spatial dimensions of the output feature map.

The stride defines the step size the filter takes as it moves across the input image. A larger stride means the filter skips more pixels, resulting in a smaller output feature map. This operation is a form of down-sampling and reduces the computational load and number of parameters in subsequent layers.

Question 13: What is the primary purpose of data augmentation in CNN training?

To artificially expand the training dataset and improve generalization (Correct answer)
To speed up inference
To reduce the number of layers
To increase model size

Correct answer: To artificially expand the training dataset and improve generalization

Data augmentation artificially expands the training dataset by applying transformations, helping CNNs generalize better to unseen data.

Question 14: What is the primary purpose of padding in a convolutional layer?

To normalize pixel values before convolution
To increase the depth of the feature maps
To reduce the number of filters
To preserve spatial dimensions of the input (Correct answer)

Correct answer: To preserve spatial dimensions of the input

Padding adds border pixels (usually zeros) around the input so the output feature map retains the same spatial size as the input.

Question 15: What is the fundamental difference between semantic segmentation and instance segmentation?

Semantic segmentation is faster
Semantic segmentation assigns the same label to all pixels of a class, while instance segmentation distinguishes individual object instances (Correct answer)
Semantic segmentation requires depth data
Instance segmentation works only on videos

Correct answer: Semantic segmentation assigns the same label to all pixels of a class, while instance segmentation distinguishes individual object instances

In semantic segmentation all pixels of the same class share one label, whereas instance segmentation distinguishes separate instances so two cars get different masks.

Question 16: Which would be the best test to establish whether a person's kidneys operate within normal ranges?

Serum glucose
Serum nitrates
Serum creatinine
Glomerular filtration rate (Correct answer)

Correct answer: Glomerular filtration rate

The Glomerular Filtration Rate (GFR) is widely considered the most accurate and comprehensive measure of overall kidney function. It estimates the volume of blood filtered by the glomeruli per unit of time, directly reflecting the kidneys' ability to remove waste products. While serum creatinine is a component used in GFR calculations, the GFR itself provides a more precise assessment of kidney health than isolated blood markers.

Question 17: How does a transposed convolution (sometimes called deconvolution) differ from a standard convolution in terms of spatial output?

It increases spatial dimensions, making it useful for upsampling (Correct answer)
It reduces spatial dimensions like a strided convolution
It operates along the channel axis rather than the spatial axes
It maintains identical spatial dimensions using same padding

Correct 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.

Question 18: Which of the following best describes the primary purpose of a 1x1 convolution operation in a CNN architecture?

To perform spatial down-sampling similar to a pooling layer.
To significantly increase the receptive field of the network.
To act as a channel-wise, fully connected layer for dimensionality reduction or expansion. (Correct answer)
To detect complex spatial features like edges and corners.

Correct answer: To act as a channel-wise, fully connected layer for dimensionality reduction or expansion.

A 1x1 convolution operates across all channels at a single pixel location. This allows it to learn combinations of features across channels, effectively acting like a fully connected layer for the channel dimension. It is widely used for dimensionality reduction (by using fewer filters than input channels) or expansion, which helps in building more efficient architectures like Inception networks.

Question 19: What is RandAugment?

A random architecture search method
An automated augmentation policy that uniformly samples from a set of augmentation operations (Correct answer)
A random dropout strategy
A random weight initialization scheme

Correct answer: An automated augmentation policy that uniformly samples from a set of augmentation operations

RandAugment simplifies augmentation search by randomly applying N operations from a fixed set, each at a global magnitude M, reducing the search space significantly.

Question 20: Which of the following assertions regarding renal illness is not true?

Kidney disease kills more people yearly than breast or prostrate cancer
Hypertension and diabetes mellitus are considered two common risk factors
Being over the age of 40 is considered a risk factor (Correct answer)
Kidney disease is treatable

Correct answer: Being over the age of 40 is considered a risk factor

While kidney function naturally declines with age, being over the age of 40 itself is not typically classified as a primary risk factor for developing kidney disease. Instead, major risk factors include conditions like hypertension (high blood pressure) and diabetes mellitus, which can damage the kidneys over time. Other significant risk factors include heart disease and a family history of kidney failure.

Question 21: In a scenario where a CNN needs to classify images by considering a smoothed-out, generalized representation of features rather than the most dominant ones, which pooling method would be the most suitable choice?

Average Pooling (Correct answer)
Stochastic Pooling
Max Pooling
Global Max Pooling

Correct answer: Average Pooling

Average pooling calculates the average of the elements in a pooling window. This has a smoothing effect on the feature map, providing a more generalized representation and preserving the overall context rather than just the most salient features.

Question 22: What problem does batch normalization primarily address?

Vanishing gradients in shallow networks
Overfitting due to excessive parameters
Exploding activations in pooling layers
Internal covariate shift across layers (Correct answer)

Correct answer: Internal covariate shift across layers

Batch normalization addresses internal covariate shift, which is the change in the distribution of layer inputs during training as preceding layer parameters change.

Question 23: What does 'feature extraction' mode mean in transfer learning?

Using PCA to reduce feature dimensions
Freezing pretrained layers and only training the new classifier head (Correct answer)
Training all layers from scratch on new data
Extracting raw pixel features before convolution

Correct answer: Freezing pretrained layers and only training the new classifier head

Feature extraction freezes the convolutional base and trains only the added classification head on the new dataset.

Question 24: In VGGNet, what architectural choice was a key design principle?

Stacking many small 3×3 convolutional filters instead of large kernels (Correct answer)
Introducing residual skip connections between layers
Using a single large 11×11 kernel in the first layer
Applying global average pooling before the classifier

Correct answer: Stacking many small 3×3 convolutional filters instead of large kernels

VGGNet demonstrated that deep networks using only 3×3 convolutions can achieve strong performance, as two 3×3 layers have the same receptive field as one 5×5 layer with fewer parameters.

Question 25: An engineer is developing a system for real-time object detection on a mobile device with limited computational power. The highest priority is inference speed, even if it means a slight trade-off in accuracy, especially for very small objects. Which object detection model architecture is most suitable for this scenario?

Faster R-CNN, because its two-stage approach with a Region Proposal Network (RPN) provides superior accuracy.
Mask R-CNN, because it extends Faster R-CNN to provide pixel-level segmentation, which is beneficial for speed.
A one-stage detector like YOLO or SSD, because it performs localization and classification in a single pass, optimizing for speed. (Correct answer)
R-CNN, because it uses an external selective search algorithm that is computationally efficient.

Correct answer: A one-stage detector like YOLO or SSD, because it performs localization and classification in a single pass, optimizing for speed.

One-stage detectors like YOLO (You Only Look Once) and SSD (Single Shot MultiBox Detector) are designed for speed and efficiency. They treat object detection as a single regression problem, directly predicting bounding boxes and class probabilities from the entire image in one pass. This contrasts with two-stage detectors like Faster R-CNN, which first generate region proposals and then classify those regions, leading to higher accuracy but slower inference times. For real-time applications on resource-constrained devices, the speed of one-stage detectors is a significant advantage.

Question 26: What is the primary role of the Region Proposal Network (RPN) in Faster R-CNN?

Propose candidate object bounding boxes (Correct answer)
Perform non-maximum suppression
Extract feature maps from the backbone
Generate class probability scores

Correct answer: Propose candidate object bounding boxes

The RPN slides over the feature map and proposes candidate bounding boxes (anchors) that may contain objects.

Question 27: Which of the following best describes the role of anchor boxes in models like Faster R-CNN and SSD?

They are used exclusively to calculate the Intersection over Union (IoU) for the final evaluation metric.
They are dynamically generated for each image to perfectly match the ground-truth objects before training begins.
They are the final, perfectly localized bounding boxes output by the model.
They are a set of predefined reference boxes of various sizes and aspect ratios used as a starting point for predicting bounding box offsets. (Correct answer)

Correct answer: They are a set of predefined reference boxes of various sizes and aspect ratios used as a starting point for predicting bounding box offsets.

Anchor boxes (also called default or prior boxes) are a set of predefined boxes with different scales and aspect ratios. Instead of predicting the absolute coordinates of a bounding box from scratch, the model predicts offsets (adjustments in position and size) relative to these anchor boxes. This approach simplifies the learning problem by turning it into a regression task of refining these initial 'guesses', making it easier for the network to detect objects of various shapes and sizes.

Question 28: The Leaky ReLU activation function was designed to address which limitation of standard ReLU?

Computational cost of exponential operations
Zero gradient for negative inputs leading to dead neurons (Correct answer)
Vanishing gradients for large positive inputs
Inability to handle multi-class outputs

Correct answer: Zero gradient for negative inputs leading to dead neurons

Leaky ReLU allows a small non-zero slope for negative inputs (e.g., 0.01x), ensuring gradients can still flow and preventing neurons from dying.

Question 29: In DenseNet, how does each layer receive its input?

From a learned weighted sum of all preceding layers
From all preceding layers via concatenation (Correct answer)
Only from the immediately preceding layer
From alternating layers spaced two apart

Correct answer: From all preceding layers via concatenation

DenseNet concatenates feature maps from all preceding layers as input to each layer, maximizing feature reuse and enabling gradient flow through the entire network.

Question 30: What problem does gradient checkpointing solve in CNN training?

Slow convergence due to poor initialization
Vanishing gradients in deep networks
Exploding gradients during training
High memory usage during backpropagation by recomputing activations (Correct answer)

Correct answer: High memory usage during backpropagation by recomputing activations

Gradient checkpointing reduces memory by not storing all intermediate activations; instead, it recomputes them during the backward pass, trading compute time for memory savings.

Question 31: When stride > 1 is used in a convolutional layer, what is the primary effect?

Spatial downsampling of the feature map (Correct answer)
Wider receptive field per filter step
Spatial upsampling of the feature map
Increased number of parameters

Correct answer: Spatial downsampling of the feature map

A larger stride causes the filter to skip positions, reducing the output spatial dimensions (downsampling).

Question 32: What is the primary goal of the Activation Maximization visualization technique when applied to a specific filter or neuron in a CNN?

To generate a synthetic image that causes the highest possible activation for that filter. (Correct answer)
To plot the distribution of activation values for that filter across the entire dataset.
To compute the gradient of the filter's output with respect to the input image pixels.
To identify which training image best activates that filter.

Correct answer: To generate a synthetic image that causes the highest possible activation for that filter.

Activation Maximization, also known as feature visualization, is an optimization process that aims to understand what a filter or neuron has learned to detect. It starts with a random noise image and iteratively modifies it using gradient ascent to find an input that maximally activates the chosen filter. The resulting synthetic image is a representation of the ideal pattern or feature that the filter is tuned to recognize.

Question 33: What does 'anchor-free' mean in the context of object detectors like FCOS?

No classification head is used
Bounding boxes are predicted without predefined anchor boxes (Correct answer)
No NMS post-processing is applied
No backbone network is used

Correct answer: Bounding boxes are predicted without predefined anchor boxes

Anchor-free detectors like FCOS predict object locations directly from feature map points without relying on predefined anchor boxes.

Question 34: What is the primary motivation for 'freezing' the early convolutional layers of a pre-trained CNN when applying transfer learning to a new task?

To significantly increase the training speed by reducing the number of backpropagation calculations.
To force the model to learn new low-level features that are highly specific to the new, smaller dataset.
To ensure that the optimizer can apply a uniform learning rate across all layers of the network.
To preserve the generic, low-level feature detectors (e.g., edges, colors, textures) that the model learned from the original large-scale dataset. (Correct answer)

Correct answer: To preserve the generic, low-level feature detectors (e.g., edges, colors, textures) that the model learned from the original large-scale dataset.

The initial layers of a CNN learn to detect general features like edges, corners, and color blobs, which are applicable to most computer vision tasks. Freezing these layers prevents their weights from being updated, thereby preserving this fundamental knowledge and preventing it from being corrupted by training on a potentially small or different dataset.

Question 35: What is the Pyramid Scene Parsing Network (PSPNet) and what problem does it address?

A network for parsing text scenes
A network that parses 3D point clouds
A recurrent network for sequential scene understanding
A segmentation network that uses a Pyramid Pooling Module to capture global and local context at multiple scales (Correct answer)

Correct answer: A segmentation network that uses a Pyramid Pooling Module to capture global and local context at multiple scales

PSPNet's Pyramid Pooling Module aggregates features at four different scales using adaptive average pooling, enabling the network to incorporate global context which reduces misclassification from local ambiguity.

Question 36: 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?

AlexNet
VGG-16
ResNet (Correct answer)
LeNet-5

Correct 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.

Question 37: What is global average pooling (GAP) and why is it used before the final classifier in modern CNNs?

It normalizes activations globally to prevent covariate shift
It averages across spatial dimensions to produce a single value per feature map, replacing dense layers (Correct answer)
It applies max pooling with a kernel equal to the full feature map size
It pools across the channel dimension to reduce depth

Correct answer: It averages across spatial dimensions to produce a single value per feature map, replacing dense layers

GAP collapses each feature map to a scalar by averaging all spatial values, drastically reducing parameters and providing some translation invariance.

Question 38: A key innovation of the GoogLeNet (Inception v1) architecture was the 'Inception module'. What is the primary purpose of this module?

To perform convolutions at multiple scales (1x1, 3x3, 5x5) in parallel and concatenate the results. (Correct answer)
To drastically increase the network depth by using residual connections.
To simplify the architecture by using only 3x3 convolutions.
To replace all fully connected layers with global average pooling to reduce parameters.

Correct answer: To perform convolutions at multiple scales (1x1, 3x3, 5x5) in parallel and concatenate the results.

The core idea of the Inception module in GoogLeNet is to allow the network to capture features at multiple scales simultaneously. It achieves this by performing 1x1, 3x3, and 5x5 convolutions, along with a max pooling operation, in parallel within the same module. The outputs are then concatenated, creating a rich, multi-scale feature representation.

Question 39: 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)?

Softmax (Correct answer)
ReLU
Sigmoid
Tanh

Correct 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.

Question 40: How does the Feature Pyramid Network (FPN) benefit CNN-based segmentation models?

It builds a multi-scale feature pyramid by combining high-resolution low-level features with semantically rich high-level features via top-down pathways (Correct answer)
It reduces the number of classes in the output
It applies pyramid-shaped attention masks
It reduces training time by skipping intermediate layers

Correct answer: It builds a multi-scale feature pyramid by combining high-resolution low-level features with semantically rich high-level features via top-down pathways

FPN creates a feature pyramid where each level has strong semantics by merging high-level features (downsampled path) with high-resolution features (bottom-up path), enabling detection and segmentation at multiple scales.

Question 41: What distinguishes a depthwise separable convolution from a standard convolution?

It applies one filter per input channel, then combines with 1×1 convolutions (Correct answer)
It replaces pooling layers entirely
It uses larger kernel sizes to capture more context
It operates only on the fully connected layers

Correct answer: It applies one filter per input channel, then combines with 1×1 convolutions

Depthwise separable convolution factorizes a standard convolution into a depthwise step (per-channel) and a pointwise 1×1 step, reducing computation.

Question 42: What architecture is U-Net primarily designed for, and what is its signature structural feature?

Biomedical image segmentation with a symmetric encoder-decoder and skip connections (Correct answer)
Image classification with residual blocks
Video segmentation with temporal convolutions
Object detection with anchor boxes

Correct answer: Biomedical image segmentation with a symmetric encoder-decoder and skip connections

U-Net is a symmetric encoder-decoder network with skip connections that directly concatenate feature maps from the encoder to the corresponding decoder level, preserving fine-grained spatial detail.

Question 43: In the Feature Pyramid Network (FPN), how are features from different levels combined?

By a transformer attention mechanism
By average pooling across levels
By top-down pathway with lateral connections (Correct answer)
By concatenation only

Correct 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.

Question 44: In progressive fine-tuning, layers are unfrozen from which direction?

Only middle layers first
From the first (input) layer forward
All layers simultaneously
From the last (output) layer backward (Correct answer)

Correct answer: From the last (output) layer backward

Progressive (gradual) fine-tuning unfreezes layers starting from the top (task-specific) toward the bottom (general) to preserve low-level features.

Question 45: In SSD (Single Shot MultiBox Detector), what is the purpose of using multiple feature map scales?

To detect objects of different sizes (Correct answer)
To apply data augmentation
To reduce inference time
To increase classification accuracy

Correct answer: To detect objects of different sizes

SSD predicts detections from feature maps at multiple resolutions, allowing it to handle both small and large objects.

Question 46: Which architecture first demonstrated that network depth beyond 20 layers could be effectively trained?

AlexNet
SqueezeNet
VGGNet
ResNet (Correct answer)

Correct answer: ResNet

ResNet (2015) successfully trained networks with 50, 101, and even 152 layers using residual connections, proving extreme depth was achievable.

Question 47: Which layer type in a CNN is responsible for introducing non-linearity?

Normalization layer
Pooling layer
Activation layer (Correct answer)
Fully connected layer

Correct answer: Activation layer

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

Question 48: In a CNN with 64 filters in a convolutional layer, how many feature maps does that layer produce per input image?

1
64 (Correct answer)
Depends on input channels
128

Correct answer: 64

Each filter produces exactly one feature map, so 64 filters yield 64 feature maps per input sample.

Question 49: A data scientist is evaluating their object detection model's performance. They are using Intersection over Union (IoU) to determine if a predicted bounding box is a true positive. What does an IoU score of 0.8 signify?

The predicted box and the ground-truth box have no overlap.
The area of the union of the two boxes is 80% of the area of their intersection.
The model is 80% confident that the object class is correct.
There is a high degree of overlap, with the area of intersection being 80% of the area of the union between the predicted and ground-truth boxes. (Correct answer)

Correct answer: There is a high degree of overlap, with the area of intersection being 80% of the area of the union between the predicted and ground-truth boxes.

Intersection over Union (IoU) is a metric used to evaluate the accuracy of a predicted bounding box by measuring how much it overlaps with the ground-truth box. It is calculated as the area of the intersection of the two boxes divided by the area of their union. An IoU score of 0.8 indicates a very good localization, as it means the shared area (intersection) is 80% of the total area covered by both boxes combined (union), signifying a strong overlap.

Question 50: In the context of a convolutional operation, what does the 'stride' parameter define?

The number of filters applied to the input volume.
The size of the pooling window used for downsampling.
The amount of zero-padding added to the borders of the input.
The number of pixels by which the filter slides over the input at each step. (Correct answer)

Correct answer: The number of pixels by which the filter slides over the input at each step.

The stride defines the step size the convolutional filter moves across the input image. A stride of 1 means the filter moves one pixel at a time. A larger stride (e.g., 2) means the filter jumps 2 pixels at each step, resulting in a smaller output feature map and reduced computation.

Question 51: What does 'dilation' (atrous convolution) add to a standard convolution?

A skip connection that bypasses the current layer
Additional convolutional channels at each layer
Extra zero-padding around the input border
Spaces between filter elements, enlarging the receptive field without increasing parameters (Correct answer)

Correct answer: Spaces between filter elements, enlarging the receptive field without increasing parameters

Dilated convolution inserts gaps (holes) between filter weights, exponentially growing the receptive field while keeping the parameter count and resolution constant.

Question 52: What is the depth of the winning ResNet model in the ILSVRC 2015 competition?

152 layers (Correct answer)
200 layers
101 layers
50 layers

Correct answer: 152 layers

The ILSVRC 2015 winning ResNet used 152 layers, achieving a top-5 error rate of 3.57%.

Question 53: What is the SegNet architecture and what distinguishes its decoder from other segmentation networks?

A network combining segmentation with depth estimation
A segmentation network whose decoder uses pooling indices from the encoder's max-pooling layers to upsample feature maps without learning upsampling weights (Correct answer)
A recurrent segmentation network for video
A network using attention for segmentation

Correct answer: A segmentation network whose decoder uses pooling indices from the encoder's max-pooling layers to upsample feature maps without learning upsampling weights

SegNet's decoder reuses the max-pooling indices (locations of selected values) stored by the encoder to perform non-linear upsampling, reducing memory requirements while preserving spatial structure.

Question 54: What is mosaic augmentation commonly used for in object detection CNN training?

Increasing image resolution
Generating mosaic art
Combining four images into a single training image to expose the model to multiple contexts simultaneously (Correct answer)
Blurring image backgrounds

Correct answer: Combining four images into a single training image to expose the model to multiple contexts simultaneously

Mosaic augmentation stitches four training images into a 2×2 grid, allowing the detector to encounter objects at different scales and positions within a single forward pass.

Question 55: What is the primary purpose of using multiple filters in a single convolutional layer?

To increase the stride
To eliminate the need for activation functions
To detect multiple distinct features simultaneously (Correct answer)
To reduce the number of parameters

Correct answer: To detect multiple distinct features simultaneously

Each filter learns to detect a different feature (e.g., edge, texture), producing one feature map per filter.

Question 56: What are dilated (atrous) convolutions and why are they used in semantic segmentation?

Convolutions applied to dilated images
Convolutions used to separate color channels
Convolutions with small kernels used to reduce computation
Convolutions with gaps between kernel elements that expand the receptive field without increasing parameters or losing resolution (Correct answer)

Correct 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.

Question 57: 38-year-old Mike Smith, a man with diabetes mellitus, has been receiving hemodialysis for two years. The partner of Mike Smith reports that he has become more aloof and uninterested, napping for most of the day. Question: To manage his depression, Mike Smith has begun taking fluoxetine 20 mg daily, an SSRI. The patient claims no improvement after two weeks. The patient needs to be informed that:

SSRIs may be ineffective for the patient
Four to six weeks are needed to evaluate response (Correct answer)
A different SSRI may be needed
The patient may respond better to other types of therapy

Correct answer: Four to six weeks are needed to evaluate response

Selective Serotonin Reuptake Inhibitors (SSRIs) typically require a period of 4 to 6 weeks, and sometimes longer, to reach their full therapeutic effect. It is common for patients not to experience significant improvement in depressive symptoms after only two weeks of treatment. Informing the patient about this expected timeframe for medication efficacy is crucial for managing expectations and ensuring adherence.

Question 58: What key innovation did Fully Convolutional Networks (FCN) introduce for semantic segmentation?

Replacing fully connected layers with convolutional layers to enable end-to-end pixel-wise prediction (Correct answer)
Using fully connected layers for dense prediction
Using recurrent layers for sequential processing
Adding attention mechanisms

Correct answer: Replacing fully connected layers with convolutional layers to enable end-to-end pixel-wise prediction

FCN replaced the fully connected layers of classification networks with convolutional layers, allowing the network to accept arbitrary-sized inputs and produce spatial output maps.

Question 59: Upon visualizing the learned filters of the first convolutional layer of a CNN trained on a large dataset of natural images (like ImageNet), which of the following patterns would you most expect to see?

Gabor-like filters detecting edges at various orientations and color blobs. (Correct answer)
Random, noisy, and uninterpretable patterns.
Fully formed objects like faces and cars.
A series of uniform, single-color squares.

Correct answer: Gabor-like filters detecting edges at various orientations and color blobs.

The first layer of a CNN processes raw pixel data. To build a hierarchical representation of the visual world, it must first learn to detect the most basic visual primitives. In natural images, these primitives are features like edges, lines, corners, and patches of color. These learned filters often resemble Gabor filters, which are used in image processing for edge and texture detection.

Question 60: What risk does overly aggressive data augmentation introduce during CNN training?

It speeds up convergence too much
It reduces memory usage
It can create unrealistic training samples that hurt model performance (Correct answer)
It always improves accuracy

Correct answer: It can create unrealistic training samples that hurt model performance

Extreme augmentations can generate semantically invalid images that mislead the network, causing it to learn incorrect feature representations and degrading accuracy.

Question 61: What are the three layers of the glomerular membrane made up of?

Endothelial
Basement membrane
Epithelial
All of the above (Correct answer)

Correct answer: All of the above

The glomerular membrane, which functions as the primary filtration barrier in the kidneys, is intricately composed of three distinct layers. These layers are the fenestrated endothelial cells of the glomerular capillaries, the glomerular basement membrane (GBM), and the podocytes (epithelial cells) that form the visceral layer of Bowman's capsule. All three layers work together to regulate the passage of substances from blood into the filtrate.

Question 62: An engineer is choosing a classic CNN architecture for a task on hardware with limited computational resources. They need a model that is deep and accurate but has a significantly lower parameter count compared to VGG-16 or AlexNet. Which architecture would be the most suitable choice?

VGG-19
GoogLeNet (Inception v1) (Correct answer)
LeNet-5
AlexNet

Correct answer: GoogLeNet (Inception v1)

GoogLeNet (Inception v1) was designed for computational efficiency. Through the heavy use of 1x1 convolutions for dimensionality reduction within its Inception modules, it achieved state-of-the-art accuracy with only about 6-7 million parameters, a fraction of AlexNet's (~60 million) and VGGNet's (~138 million) parameters.

Question 63: Which of the following is a key architectural requirement for generating a classic Class Activation Map (CAM) to visualize where a CNN is 'looking'?

The network must be trained using a sigmoid activation function in all layers.
The network must use only 3x3 convolutional filters.
The network must not contain any pooling layers.
The network must have a Global Average Pooling (GAP) layer followed by a dense output layer. (Correct answer)

Correct answer: The network must have a Global Average Pooling (GAP) layer followed by a dense output layer.

The original Class Activation Mapping (CAM) technique requires a specific network architecture. The final convolutional layer must be followed by a Global Average Pooling (GAP) layer, which is then connected to a final dense (fully-connected) layer for classification. This structure allows the weights from the dense layer to be used to create a weighted sum of the preceding feature maps, generating the heatmap.

Question 64: In object detection, what is the primary purpose of the Non-Maximum Suppression (NMS) algorithm?

To generate a diverse set of initial region proposals across the entire image.
To select the single best bounding box for an object from multiple overlapping predictions. (Correct answer)
To increase the number of bounding boxes for each object to improve recall.
To calculate the classification loss for each predicted bounding box.

Correct answer: To select the single best bounding box for an object from multiple overlapping predictions.

Non-Maximum Suppression (NMS) is a crucial post-processing step in object detection. Models often output multiple, highly overlapping bounding boxes for the same object. NMS cleans up these redundant detections by iteratively selecting the box with the highest confidence score and suppressing (removing) other nearby boxes that have a high Intersection over Union (IoU) with the selected box. This ensures that each detected object is represented by only one bounding box in the final output.

Question 65: Which of the following is a defining characteristic of one-stage object detectors like SSD (Single Shot MultiBox Detector)?

They first generate region proposals and then pass each proposal to a separate classifier.
They use a computationally expensive selective search to find interesting regions first.
They require each image to be processed multiple times to find all objects.
They make predictions on a dense grid of locations across feature maps of multiple scales. (Correct answer)

Correct answer: They make predictions on a dense grid of locations across feature maps of multiple scales.

A key feature of one-stage detectors like SSD is that they bypass the explicit region proposal step found in two-stage detectors. Instead, they apply a set of convolutional filters to feature maps at different scales in the network. At each location on these feature maps (a dense grid), the model predicts bounding box offsets and class probabilities simultaneously. Using multiple feature maps allows the model to detect objects of various sizes in a single forward pass.

Question 66: Which operation sums element-wise products between a filter and a receptive field in a CNN?

Dot product of flattened tensors
Convolution without flipping
Matrix multiplication
Cross-correlation (Correct answer)

Correct answer: Cross-correlation

Cross-correlation (often loosely called convolution in deep learning) computes the sum of element-wise products without flipping the filter.

Question 67: What is the key innovation in MobileNetV2's inverted residual block compared to standard residual blocks?

It replaces ReLU with sigmoid to prevent dead neurons
It uses dilated convolutions to increase receptive field without more parameters
It expands channels before the depthwise convolution, then compresses with a linear bottleneck (Correct answer)
It applies group convolutions to split channels into independent subgroups

Correct answer: It expands channels before the depthwise convolution, then compresses with a linear bottleneck

MobileNetV2 inverts the bottleneck by expanding channels first, applying depthwise conv, then projecting back to a low-dimensional space with a linear activation.

Question 68: What does the mean Intersection over Union (mIoU) metric measure in semantic segmentation evaluation?

The ratio of true positives to total predictions
The average pixel accuracy across all images
The mean number of correctly detected objects
The average of per-class IoU scores, where IoU measures overlap between predicted and ground-truth masks (Correct answer)

Correct 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.

Question 69: Which loss function does YOLO use for bounding box coordinate regression?

Cross-entropy loss
IoU loss
Focal loss
Mean squared error (MSE) (Correct answer)

Correct answer: Mean squared error (MSE)

Original YOLO uses MSE for coordinate regression, though later versions switched to IoU-based losses.

Question 70: What filter size does VGGNet use exclusively in its convolutional layers?

1x1
3x3 (Correct answer)
5x5
7x7

Correct answer: 3x3

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

Question 71: A developer is building a flower species classifier using a small, custom dataset of approximately 900 images. They decide to use a ResNet50 model pre-trained on ImageNet. To leverage the pre-trained features effectively while minimizing the risk of overfitting, which transfer learning strategy should they implement first?

Unfreeze all layers and fine-tune the entire network using a high learning rate.
Freeze all convolutional layers and train only a new, randomly initialized classifier head. (Correct answer)
Train the entire network from scratch with randomly initialized weights.
Remove the first few convolutional layers and retrain the rest of the network on the new dataset.

Correct answer: Freeze all convolutional layers and train only a new, randomly initialized classifier head.

With a small dataset, there is a high risk of overfitting if the entire network is trained. The best initial strategy is feature extraction, which involves freezing the pre-trained convolutional layers to use their powerful, generic feature detection capabilities and only training the new classifier head on the small dataset.

Question 72: In a CNN, a 4×4 feature map with a 2×2 max pooling kernel and stride 2 produces an output of what size?

3×3
4×4
2×2 (Correct answer)
1×1

Correct 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.

Question 73: Which metric best indicates whether a source domain is suitable for transfer to a target domain?

Batch size used during source training
Depth of the source CNN
Domain similarity or distribution overlap (Correct answer)
Number of parameters in the source model

Correct answer: Domain similarity or distribution overlap

Domain similarity determines how transferable the learned features are; high similarity means better transfer.

Question 74: Which of the following best describes the strategy of 'fine-tuning' in the context of transfer learning with a pre-trained CNN?

Using the pre-trained model as a static feature extractor without updating any of its original weights.
Training only the batch normalization layers while keeping all convolutional and fully connected layers frozen.
Replacing the final classification layer and subsequently unfreezing some of the later convolutional layers to continue training them on the new data, typically with a very low learning rate. (Correct answer)
Adding new, randomly initialized convolutional layers to the beginning of the pre-trained network to learn domain-specific features.

Correct answer: Replacing the final classification layer and subsequently unfreezing some of the later convolutional layers to continue training them on the new data, typically with a very low learning rate.

Fine-tuning involves not only replacing the classifier head but also unfreezing some of the deeper, more specialized layers of the pre-trained model. These layers are then trained on the new dataset with a low learning rate to subtly adjust their weights to the new task without drastically altering the learned features.

Question 75: During the training of a deep CNN, a practitioner observes that the distribution of inputs to deeper layers is constantly changing, a phenomenon known as internal covariate shift. This slows down training because the layers must continually adapt to a new distribution. Which technique is specifically designed to mitigate this problem by normalizing the inputs to each layer?

Learning Rate Annealing
L2 Regularization
Batch Normalization (Correct answer)
Gradient Clipping

Correct answer: Batch Normalization

Batch Normalization is a technique designed to reduce internal covariate shift. [11] It normalizes the output of a previous activation layer by subtracting the batch mean and dividing by the batch standard deviation. [9, 11] This stabilization of the distributions of layer inputs allows for faster training, higher learning rates, and can act as a form of regularization. [10, 11]

Question 76: Which technique involves training the CNN with the true label replaced by a soft distribution over all classes to reduce overconfidence?

Temperature scaling
Mixup
Knowledge distillation
Label smoothing (Correct answer)

Correct answer: Label smoothing

Label smoothing replaces hard one-hot targets with soft targets (e.g., 0.9 for correct class, 0.1/K for others) to prevent over-confident predictions.

Question 77: A CNN model achieves 99% accuracy on the training dataset but only 75% on the validation dataset. Which phenomenon is occurring, and what is a common technique to address it?

Vanishing gradients; switch to a different activation function like Leaky ReLU.
Overfitting; apply Dropout to the fully connected layers. (Correct answer)
Underfitting; increase model complexity by adding more layers.
Data leakage; remove features that are present in both training and validation sets.

Correct answer: Overfitting; apply Dropout to the fully connected layers.

The significant performance gap between training and validation accuracy is a classic sign of overfitting, where the model has learned the training data too well, including its noise, and fails to generalize to new data. [24, 27] Dropout is a widely used regularization technique that randomly sets a fraction of neuron activations to zero during training, which helps prevent complex co-adaptations and improves generalization. [3, 18, 20]

Question 78: During CNN training, which data augmentation technique generates new training samples by combining two images and their labels linearly?

CutMix
Mixup (Correct answer)
Cutout
Random Erasing

Correct answer: Mixup

Mixup creates training samples as convex combinations of pairs of training examples and their labels.

Question 79: Towards the end of a CNN architecture, after the convolutional and pooling layers have extracted features, which layer is typically responsible for taking these high-level features and performing the final classification task?

A max-pooling layer
Another convolutional layer
A fully connected (dense) layer (Correct answer)
An activation layer like ReLU

Correct answer: A fully connected (dense) layer

The fully connected (or dense) layer takes the high-level features from the preceding layers (which are often flattened into a 1D vector) and performs the final classification. Each neuron in a fully connected layer is connected to all neurons in the previous layer, allowing it to learn non-linear combinations of these features to make a prediction.

Question 80: A team is training a CNN for image classification on a dataset with limited samples. They notice the training accuracy is very high, but the validation accuracy is significantly lower and has plateaued. Which of the following techniques is specifically designed to address this issue by creating an ensemble of smaller networks during training?

Data Augmentation
Dropout (Correct answer)
Batch Normalization
Adam Optimizer

Correct answer: Dropout

Dropout is a regularization technique that randomly sets a fraction of neuron activations to zero during each training step. [5] This prevents neurons from co-adapting too much and forces the network to learn more robust features, effectively training an ensemble of many smaller networks. [5, 7] This process helps to reduce overfitting, which is characterized by high training accuracy and poor validation/test accuracy. [22]

Question 81: What is the role of skip connections in the U-Net architecture?

They connect non-adjacent layers for gradient flow only
They skip low-performing layers during inference
They pass high-resolution feature maps from the encoder to the decoder to recover spatial detail lost during downsampling (Correct answer)
They skip residual computations to speed up training

Correct answer: They pass high-resolution feature maps from the encoder to the decoder to recover spatial detail lost during downsampling

Skip connections concatenate encoder feature maps with decoder feature maps at matching resolutions, allowing the decoder to recover fine spatial details that are lost during pooling.

Question 82: In the context of CNNs, what does 'weight sharing' mean and why is it important?

Weights are shared between the encoder and decoder paths
The same filter weights are applied at every spatial location, drastically reducing parameters (Correct answer)
Convolutional and fully connected layers reuse the same weight matrix
Multiple layers share the same weights to save memory

Correct answer: The same filter weights are applied at every spatial location, drastically reducing parameters

Weight sharing means one learned filter slides across the entire input, so a layer with a 3×3 filter has only 9 weights per channel regardless of input size.

Question 83: What is Mixup augmentation in CNN training?

Randomly mixing color channels
Creating synthetic samples by linearly interpolating between two training images and their labels (Correct answer)
Mixing different optimizers
Combining multiple loss functions

Correct answer: Creating synthetic samples by linearly interpolating between two training images and their labels

Mixup blends two training images and their corresponding labels by a random ratio λ, encouraging the model to learn smoother decision boundaries.

Question 84: What is Test-Time Augmentation (TTA) used for in CNN inference?

Speeding up inference time
Augmenting the test dataset permanently
Applying multiple augmentations to test images and averaging predictions to improve accuracy (Correct answer)
Reducing model parameters at test time

Correct answer: Applying multiple augmentations to test images and averaging predictions to improve accuracy

TTA applies several augmented versions of each test image, collects the model's predictions for each, and averages them to produce a more robust final prediction.

Question 85: Diana Walsh, a 62-year-old woman receiving hemodialysis, complains of constant scratching. Question: When the patient's Kt/V is 1.1, and Ms. Walker's itchiness doesn't go away, the first dialysis adjustment should be to

Increase Kt/V to >1.5
Increase Kt/V to >1.2 (Correct answer)
Increase Kt/V to >1.1
Decrease Kt/V to <1.0

Correct answer: Increase Kt/V to >1.2

Kt/V is a crucial measure of dialysis adequacy, indicating the effectiveness of toxin removal. If a patient experiences persistent itching (uremic pruritus) with a Kt/V of 1.1, it suggests that the current dialysis dose might be insufficient to adequately clear uremic toxins. The recommended first adjustment is to increase the dialysis dose, aiming for a higher Kt/V, typically greater than 1.2, to improve solute clearance and potentially alleviate symptoms.

Question 86: Sanda Miller, a 46-year-old woman, underwent CAPD after developing chronic glomerulonephritis-related kidney failure. Question: A catheter-related mass has grown on Ms. Miller's body. The most frequent way to tell a hernia apart from a hematoma or seroma is to

Have the patient stand and bear down
Evaluate through auscultation and palpitation
Examine with CT scan
Examine with an ultrasound (Correct answer)

Correct answer: Examine with an ultrasound

An ultrasound is the most effective and non-invasive diagnostic tool to differentiate between a hernia, hematoma, or seroma in a CAPD patient. Ultrasound imaging can clearly visualize internal structures, identify the presence of bowel loops (indicating a hernia), or fluid collections (seroma/hematoma), and assess their characteristics, providing a definitive diagnosis without more invasive procedures.

Question 87: Which of the following best describes the role of the convolutional layer in a CNN?

To classify the input by connecting every neuron from the previous layer.
To flatten the multi-dimensional feature maps into a one-dimensional vector.
To apply a set of learnable filters to the input data to create feature maps. (Correct answer)
To reduce the number of parameters in the network through downsampling.

Correct answer: To apply a set of learnable filters to the input data to create feature maps.

The convolutional layer is the core building block of a CNN. Its primary function is to apply a series of learnable filters (or kernels) that slide over the input image to detect specific features like edges, corners, and textures, resulting in feature maps.

Question 88: How does a 1×1 convolution (pointwise convolution) affect a feature map?

It acts as a pooling operation
It increases spatial resolution
It changes the number of channels without altering spatial dimensions (Correct answer)
It applies spatial filtering across a local region

Correct answer: It changes the number of channels without altering spatial dimensions

A 1×1 convolution performs a linear combination across channels at each spatial position, enabling channel dimensionality reduction or expansion.

Question 89: Which of the following would be valid with using EPO (epoetin alfa) during hemodialysis?

To help produce white blood cells
To stimulate red blood cell production (Correct answer)
To help prevent pain in their joints
None of the above

Correct answer: To stimulate red blood cell production

Epoetin alfa (EPO) is a synthetic form of erythropoietin, a hormone naturally produced by healthy kidneys. In patients with chronic kidney disease, the damaged kidneys often fail to produce sufficient erythropoietin, leading to anemia. Administering EPO during hemodialysis stimulates the bone marrow to produce red blood cells, effectively treating or preventing anemia and improving patient well-being.

Question 90: Which optimizer introduces a per-parameter adaptive learning rate based on the second moment of gradients?

Adagrad
RMSprop
Adam (Correct answer)
SGD with momentum

Correct answer: Adam

Adam maintains both first moment (mean) and second moment (uncentered variance) estimates of gradients, providing adaptive per-parameter learning rates with bias correction.

Question 91: In EfficientNet, what is 'compound scaling' and what does it scale jointly?

Alternating between scaling width and depth in even and odd layers
Scaling the learning rate and batch size together during training
Scaling only depth to add more residual blocks uniformly
Jointly scaling network width, depth, and input resolution using a fixed ratio (Correct answer)

Correct answer: Jointly scaling network width, depth, and input resolution using a fixed ratio

EfficientNet's compound scaling coefficient φ uniformly scales width (channels), depth (layers), and resolution (input size) with empirically derived ratios.

Question 92: What is the spatial dimension relationship between an input feature map and output feature map when using a 3×3 filter with padding='same' and stride=1?

Output size depends only on the number of filters
Output is larger by 2 in each dimension
Output is smaller by 2 in each dimension
Output is the same spatial size as the input (Correct answer)

Correct answer: Output is the same spatial size as the input

With 'same' padding and stride=1, zero-padding is added so the output spatial dimensions exactly match the input dimensions.

Question 93: Global Average Pooling (GAP) is frequently used at the end of a CNN to replace which traditional layer?

Dropout layer
Batch normalization layer
Convolutional layer
Fully connected (dense) layer (Correct answer)

Correct answer: Fully connected (dense) layer

GAP reduces each feature map to a single value, replacing large fully connected layers and dramatically reducing parameter count.

Question 94: Which of the following data augmentation techniques would be least appropriate for a CNN designed to classify handwritten digits from the MNIST dataset, where the orientation of the digit is a key feature?

Small scaling (zooming in/out)
Minor translation (shifting)
Slight rotation (e.g., +/- 10 degrees)
Random vertical flipping (Correct answer)

Correct answer: Random vertical flipping

Data augmentation should create realistic variations of the training data while preserving the correct label. [29] For handwritten digits, a vertical flip would often change the digit into a different, non-existent, or incorrect digit (e.g., a '6' could look like a '9', but flipping a '6' vertically does not result in a valid '6'). Slight rotations, translations, and scaling are all plausible variations of handwriting and are therefore appropriate augmentation techniques. [4]

Question 95: Which architecture introduced the concept of 'network-in-network' using micro neural networks at each convolutional step?

SqueezeNet
Network-in-Network (NIN) (Correct answer)
VGGNet
AlexNet

Correct answer: Network-in-Network (NIN)

NIN replaced standard convolutional filters with small multi-layer perceptrons (mlpconv layers) at each location, enabling more complex feature extraction per patch.

Question 96: Which metric is typically used to evaluate object detection performance?

F1 score
Mean Average Precision (mAP) (Correct answer)
Pixel accuracy
Top-5 accuracy

Correct answer: Mean Average Precision (mAP)

mAP averages the Average Precision across all object classes and IoU thresholds, making it the standard detection metric.

Question 97: Which of the following was a key innovation introduced in the AlexNet architecture that distinguished it from its predecessor, LeNet-5?

The use of average pooling for subsampling.
A shallow architecture with only 5 layers.
The use of the Rectified Linear Unit (ReLU) activation function. (Correct answer)
The introduction of the Inception module.

Correct answer: The use of the Rectified Linear Unit (ReLU) activation function.

While LeNet-5 used sigmoid or tanh activation functions, AlexNet was one of the first major architectures to popularize the use of the Rectified Linear Unit (ReLU). ReLU helped to significantly speed up the training process and mitigate the vanishing gradient problem, which was a major advantage for the deeper, 8-layer AlexNet architecture.

Question 98: In a typical Convolutional Neural Network (CNN) architecture, what is the primary function of the pooling layer?

To introduce non-linearity into the model.
To extract features like edges and textures from the input image.
To reduce the spatial dimensions of the feature maps. (Correct answer)
To perform classification based on extracted features.

Correct answer: To reduce the spatial dimensions of the feature maps.

The pooling layer, also known as a downsampling layer, is primarily used to reduce the spatial dimensions (width and height) of the input feature maps. This process helps to decrease the computational complexity, control overfitting, and create an invariance to small translations in the input image.

Question 99: In CNN training, what does the term 'augmentation policy' refer to?

The GPU policy for running training
The learning rate schedule
The model regularization method
A defined set of transformation operations along with their probabilities and magnitudes (Correct answer)

Correct answer: A defined set of transformation operations along with their probabilities and magnitudes

An augmentation policy specifies which transformations to apply, with what probability each is chosen, and at what intensity level, forming a complete augmentation strategy.

Question 100: What is the main purpose of using the ReLU (Rectified Linear Unit) activation function in the hidden layers of a CNN?

To convert the output into a probability distribution for classification.
To normalize the output of the layer to have a mean of zero.
To significantly increase the number of parameters for better feature extraction.
To introduce non-linearity, allowing the network to learn more complex patterns. (Correct answer)

Correct answer: To introduce non-linearity, allowing the network to learn more complex patterns.

The ReLU activation function introduces non-linearity into the network. Without a non-linear activation function, a deep CNN would behave like a single, equivalent convolutional layer, limiting its ability to learn complex relationships in the data. ReLU is computationally efficient and helps mitigate the vanishing gradient problem.

Question 101: A data scientist is training a CNN on a small, specialized dataset of industrial parts. To prevent the model from memorizing the limited training examples, they decide to artificially expand the dataset. Which of the following techniques are they employing?

L2 Regularization
Early Stopping
Principal Component Analysis (PCA)
Data Augmentation (Correct answer)

Correct answer: Data Augmentation

Data augmentation is the process of artificially increasing the size of a training dataset by creating modified versions of the existing data. [15, 17] For images, this includes techniques like rotation, flipping, scaling, and color shifting. [4, 12, 18] This helps the model generalize better by exposing it to a wider variety of training examples, which is a powerful method for combating overfitting, especially with small datasets. [1, 15]

Question 102: What is the purpose of random rotation augmentation in CNN training?

To reduce image dimensions
To normalize pixel values
To make the model invariant to the orientation of objects in the image (Correct answer)
To speed up training convergence

Correct answer: To make the model invariant to the orientation of objects in the image

Random rotation augmentation rotates training images by a random angle, teaching the CNN to recognize objects regardless of their orientation.

Question 103: Which of the following statements about acute renal failure would be judged to be the most accurate?

Acute renal failure comes on suddenly and typically lasts only a short period (Correct answer)
None of the above
An acute episode of chronic renal failure lasts for only three weeks.

Correct answer: Acute renal failure comes on suddenly and typically lasts only a short period

Acute renal failure (ARF), also known as acute kidney injury (AKI), is characterized by a sudden and rapid decline in kidney function. Unlike chronic kidney disease, which develops slowly over months or years, ARF typically has an abrupt onset and can often be reversible with timely and appropriate medical intervention, meaning its duration is usually short-term.

Question 104: What are the two learnable parameters introduced by batch normalization?

Mean (mu) and variance (sigma)
Scale (gamma) and shift (beta) (Correct answer)
Weight decay (lambda) and dropout rate (p)
Learning rate (alpha) and momentum (beta)

Correct answer: Scale (gamma) and shift (beta)

Batch normalization introduces gamma (scale) and beta (shift) parameters that allow the network to undo the normalization if needed, learned during training.

Question 105: What is the encoder-decoder architecture in CNN-based segmentation networks?

A GAN-based structure for generating masks
An autoencoder used for image compression
A two-stage classifier followed by a regressor
A network where the encoder downsamples the input to a bottleneck and the decoder upsamples it back to the original resolution for pixel prediction (Correct answer)

Correct answer: A network where the encoder downsamples the input to a bottleneck and the decoder upsamples it back to the original resolution for pixel prediction

The encoder extracts hierarchical features while reducing spatial resolution, and the decoder gradually upsamples these features back to the input resolution to produce the segmentation map.

Question 106: In a CNN, what does 'stride' control?

The number of channels in the output
The learning rate during backpropagation
How many pixels the filter moves between applications (Correct answer)
The depth of the convolutional filter

Correct 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.

Question 107: What problem does Non-Maximum Suppression (NMS) solve in object detection?

Multiple overlapping predictions for the same object (Correct answer)
Underfitting of the classification head
Gradient vanishing in deep networks
Class imbalance during training

Correct answer: Multiple overlapping predictions for the same object

NMS removes redundant bounding boxes by keeping only the highest-scoring box among overlapping predictions for the same object.

Question 108: What is the output size formula for a convolutional layer given input W, filter F, padding P, and stride S?

(W + 2P - F) / S + 1 (Correct answer)
(W * F) / (P + S)
(W - F + 2P) * S
(W + F - 2P) / S - 1

Correct answer: (W + 2P - F) / S + 1

The spatial output size is computed as (W + 2P − F) / S + 1, which accounts for padding, filter size, and the step size.

Question 109: A deep CNN with many layers is tested without any regularization on a small dataset. Which problem is MOST likely?

Exploding activations only
Vanishing gradients only
Underfitting due to too many parameters
Overfitting due to excess model capacity (Correct answer)

Correct answer: Overfitting due to excess model capacity

A high-capacity model (many parameters) on a small dataset will memorize training examples, causing overfitting.

Question 110: What is the primary advantage of using depthwise convolutions over standard convolutions in terms of computational cost?

They reduce multiply-add operations by separating spatial and channel-wise filtering (Correct answer)
They allow arbitrarily large kernel sizes without extra cost
They eliminate the need for activation functions
They require more memory but execute faster on GPU

Correct answer: They reduce multiply-add operations by separating spatial and channel-wise filtering

Depthwise convolutions apply one filter per input channel independently, reducing the number of multiply-add operations by a factor roughly equal to the number of output channels.

Question 111: In the Inception module (GoogLeNet), why are convolutions of different kernel sizes applied in parallel?

To eliminate the need for pooling layers
To capture features at multiple scales simultaneously within the same layer (Correct answer)
To reduce the number of training epochs needed
To enforce weight sharing across different resolution branches

Correct answer: To capture features at multiple scales simultaneously within the same layer

Parallel branches with 1×1, 3×3, and 5×5 filters let the Inception module learn features at multiple spatial scales and concatenate them along the depth axis.

Question 112: When visualizing early-layer feature maps, what kind of patterns are typically detected?

Abstract semantic concepts
Class probability distributions
Low-level patterns like edges, colors, and textures (Correct answer)
Complex object parts like eyes or wheels

Correct answer: Low-level patterns like edges, colors, and textures

Early CNN layers respond to simple, low-level visual features such as oriented edges, color gradients, and basic textures.

Question 113: If a feature map appears mostly dark (near-zero activations), what does this indicate?

The layer uses sigmoid activation
The filter's learned pattern is not present in the input region (Correct answer)
The input image is too large
The filter is perfectly trained

Correct answer: The filter's learned pattern is not present in the input region

Near-zero activations mean the convolutional filter did not detect its corresponding pattern in those spatial locations of the input.

Question 114: Dialysate glucose must be heat sterilized at a low pH to

Prevent the dialysate from becoming cloudy
Prevent crystallization in the dialysate
Increase generation of glucose degradation products
Decrease generation of glucose degradation products (Correct answer)

Correct answer: Decrease generation of glucose degradation products

Dialysate glucose must be heat sterilized at a low pH to minimize the formation of glucose degradation products (GDPs). High temperatures combined with a neutral or alkaline pH during sterilization can cause glucose to break down into harmful GDPs. These GDPs are associated with inflammation and damage to the peritoneal membrane in peritoneal dialysis patients, so maintaining a low pH helps preserve the integrity of the dialysate.

Question 115: Which PyTorch library is most commonly used for applying data augmentation transforms to image datasets?

torch.nn
torchvision.transforms (Correct answer)
torch.optim
torch.utils.data

Correct answer: torchvision.transforms

torchvision.transforms provides a comprehensive set of image augmentation operations such as RandomHorizontalFlip, RandomCrop, and ColorJitter.

Question 116: What does the learning rate scheduler 'ReduceLROnPlateau' do when validation loss stops improving?

Stops training immediately
Reduces the learning rate by a factor (Correct answer)
Resets the model weights
Increases the learning rate by a factor

Correct answer: Reduces the learning rate by a factor

ReduceLROnPlateau monitors a metric and reduces the learning rate by a specified factor when no improvement is seen for a patience number of epochs.

Question 117: What loss function is most commonly used as the primary training objective in semantic segmentation CNNs?

Triplet Loss
Pixel-wise Cross-Entropy Loss (Correct answer)
Mean Squared Error (MSE)
Hinge Loss

Correct answer: Pixel-wise Cross-Entropy Loss

Pixel-wise cross-entropy treats each pixel as an independent classification problem and sums the cross-entropy loss over all pixels, making it the standard choice for semantic segmentation training.

Question 118: In CNN training, what does 'warm restarts' refer to in the context of learning rate schedules?

Gradually increasing batch size
Periodically resetting the learning rate to a high value then annealing it (Correct answer)
Restarting training from scratch periodically
Warming up GPU memory before training

Correct answer: Periodically resetting the learning rate to a high value then annealing it

Warm restarts (SGDR) periodically resets the learning rate to a maximum value and then follows a cosine annealing schedule, helping the model explore different loss landscape regions.

Question 119: According to him, one of Mr Adler's main concerns is that he can no longer perform a full-time job but is not qualified for Medicaid. The patient worries that he will be unable to afford his insurance. The entity that might offer financial support is the

American Kidney Fund (Correct answer)
National Organization for Renal Disease
American Association of Kidney Patients
National Kidney Foundation

Correct answer: American Kidney Fund

The American Kidney Fund (AKF) is a national non-profit organization specifically dedicated to providing financial assistance to kidney patients. This includes help with health insurance premiums, co-pays, and other medical expenses. Given Mr. Adler's concerns about affording insurance due to kidney-related issues, the AKF is the most relevant and direct source of financial support.

Question 120: In a fully convolutional network (FCN), what replaces the fully connected layers to enable pixel-wise predictions?

Additional pooling layers to collapse the feature map
Global max pooling across spatial dimensions
Dropout layers applied at every spatial location
Transposed convolutions (or bilinear upsampling) to recover spatial resolution (Correct answer)

Correct answer: Transposed convolutions (or bilinear upsampling) to recover spatial resolution

FCNs replace dense layers with convolutional ones and use transposed convolutions to upsample feature maps back to the input resolution for dense prediction.

Question 121: What problem do residual connections in ResNet primarily solve?

Slow inference speed during deployment
Excessive memory usage from large feature maps
Overfitting on small datasets
Vanishing gradients that hinder training of very deep networks (Correct answer)

Correct answer: Vanishing gradients that hinder training of very deep networks

Residual (skip) connections allow gradients to flow directly through the network, mitigating vanishing gradient problems that arise in very deep architectures.

Question 122: What is the effect of using a very large learning rate when training a CNN with batch normalization?

It immediately causes NaN losses due to BN's variance computation
It causes gradient values to be clipped by BN, preventing learning
It can be tolerated better than without BN because BN stabilizes the distribution of layer inputs (Correct answer)
It has no effect because BN removes the dependence on learning rate scale

Correct answer: It can be tolerated better than without BN because BN stabilizes the distribution of layer inputs

Batch Normalization reduces sensitivity to learning rate by normalizing activations, allowing higher rates that would cause instability in unnormalized networks.

Question 123: A team is adapting a powerful ImageNet pre-trained model for a new task of classifying industrial machine parts from a large, proprietary dataset of over 200,000 images. The visual characteristics of the machine parts are significantly different from the natural images in ImageNet. What is the most effective transfer learning approach?

Discard the pre-trained weights and train the entire model from scratch on the new dataset.
Freeze the entire pre-trained model and only train a new classifier head.
Unfreeze most or all of the layers and fine-tune the entire network using the pre-trained weights as a starting point. (Correct answer)
Use only the final fully connected layers from the pre-trained model and build a new convolutional base.

Correct answer: Unfreeze most or all of the layers and fine-tune the entire network using the pre-trained weights as a starting point.

Because the new dataset is large, there is less risk of overfitting. Since the data domain is different, the model needs to learn more specialized features. The optimal approach is to use the pre-trained weights as a superior alternative to random initialization and fine-tune the entire network, allowing it to adapt its learned features to the new domain of machine parts.

Question 124: The gradient of a substance's concentration, such as urea, during peritoneal dialysis

Remains consistent
Increases
Decreases (Correct answer)
Varies widely

Correct 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.

Question 125: What is 'negative transfer' in the context of transfer learning with CNNs?

When pretraining hurts performance on the target task (Correct answer)
Training on negative examples only
Transferring weights with negative values
Transfer learning that reduces model size

Correct 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.

Question 126: 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?

Increasing the stride of the convolution.
Using a larger pooling window.
Adding a padding layer around the input images. (Correct answer)
Implementing a dropout layer after the convolutional layer.

Correct 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.

Question 127: 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.

Hardiness
Resilience (Correct answer)
Self-efficacy
Sense of belonging

Correct 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.

Question 128: For more than 30 years, renal replacement therapy (RRT) has been in use. Which of the following is accurate for the approximate mortality rate of the patient with ARF (acute renal failure) despite the time this therapy has been used?

90%
30%
50% (Correct answer)
10%

Correct answer: 50%

Despite significant advancements in renal replacement therapy (RRT) over several decades, the mortality rate for patients experiencing acute renal failure (ARF) remains remarkably high. Clinical studies and data consistently indicate that approximately 50% of patients, particularly those with severe ARF or in critical care settings, do not survive, underscoring the serious nature and challenges in treating this condition.

Question 129: The process in a convolutional layer where a filter slides over the input data, computes element-wise products, and sums them up to create a single value in the output is known as what?

Max Pooling
Convolution (Correct answer)
Activation
Flattening

Correct answer: Convolution

This describes the fundamental convolution operation. The filter (or kernel) moves across the input, and at each position, the dot product between the filter's weights and the corresponding input values is calculated. This result forms one element of the output feature map.

Question 130: Why is batch normalization particularly important in semantic segmentation CNN training?

It reduces the number of output classes
It increases the spatial resolution of feature maps
It normalizes feature map activations across the batch to stabilize training and reduce sensitivity to weight initialization (Correct answer)
It augments the training data automatically

Correct answer: It normalizes feature map activations across the batch to stabilize training and reduce sensitivity to weight initialization

Batch normalization normalizes activations within each mini-batch, reducing internal covariate shift and enabling higher learning rates, which is critical for the deep encoder-decoder architectures common in segmentation.

Question 131: In AlexNet, what was the purpose of Local Response Normalization (LRN)?

To normalize activations across neighboring feature maps for lateral inhibition (Correct answer)
To scale gradients during backpropagation
To replace dropout during training
To reduce the spatial size of feature maps

Correct answer: To normalize activations across neighboring feature maps for lateral inhibition

LRN in AlexNet suppresses activations that are weak relative to neighbors across channels, mimicking lateral inhibition seen in biological neurons.

Question 132: Cease having dialysis. Which of the following claims regarding their choice is true?

It is regarded as euthanasia if the patient elects to stop receiving dialysis
According to the guidelines, the doctor should stop providing supportive care to the patient if they choose to stop receiving dialysis
If the patient decides to withdraw from dialysis, it is not considered euthanasia (Correct answer)
The patient does not have the option to stop receiving dialysis once treatment has begun

Correct answer: If the patient decides to withdraw from dialysis, it is not considered euthanasia

Patients have the fundamental right to autonomy and can refuse or withdraw from medical treatment, even life-sustaining therapies like dialysis, at any point. This decision is considered an exercise of patient rights and is distinct from euthanasia, which involves a physician actively administering a lethal substance to end a patient's life. Withdrawing from treatment is a passive act of allowing the natural course of illness to proceed.

Question 133: A data scientist is designing a CNN to classify high-resolution medical images where preserving spatial information in the early layers is critical. Which hyperparameter setting for the initial convolutional layers would be most appropriate?

No padding ('valid') and a stride of 2.
Small filter size (e.g., 3x3), stride of 1, and 'same' padding. (Correct answer)
Large filter size (e.g., 11x11) and a large stride (e.g., 4).
A 1x1 filter with a stride of 1.

Correct answer: Small filter size (e.g., 3x3), stride of 1, and 'same' padding.

To preserve spatial information, it is best to avoid aggressive down-sampling in the early layers. A small filter size (3x3) captures local features, a stride of 1 ensures the filter moves pixel-by-pixel without skipping information, and 'same' padding ensures that the output feature map has the same spatial dimensions as the input, preventing information loss at the borders.

Question 134: What role does Batch Normalization play in CNN training?

It clips gradient values to prevent exploding gradients
It normalizes layer inputs per mini-batch, stabilizing and accelerating training (Correct answer)
It rescales weight matrices to unit norm after each update
It randomly drops entire feature maps to improve generalization

Correct answer: It normalizes layer inputs per mini-batch, stabilizing and accelerating training

Batch Normalization normalizes activations to zero mean and unit variance per mini-batch, reducing internal covariate shift and allowing higher learning rates.

Question 135: What is GridDistortion augmentation used for in CNN training?

Resizing images to a grid size
Applying grid-based masking
Applying elastic deformation by displacing image grid points to simulate geometric variability (Correct answer)
Adding grid lines to images

Correct answer: Applying elastic deformation by displacing image grid points to simulate geometric variability

GridDistortion applies non-linear geometric deformations by shifting the intersection points of a grid, helping models become invariant to slight spatial distortions.

Question 136: What is the primary goal of using regularization techniques like Dropout or L2 regularization when training a Convolutional Neural Network?

To increase the speed of convergence during training.
To increase the model's performance on the training dataset.
To reduce the model's complexity and improve its ability to generalize to unseen data. (Correct answer)
To automatically determine the optimal number of convolutional layers.

Correct answer: To reduce the model's complexity and improve its ability to generalize to unseen data.

The fundamental purpose of regularization is to prevent overfitting. [2, 12] Overfitting occurs when a model learns the training data too well and fails to generalize to new, unseen data. [24, 27] Regularization techniques introduce constraints or penalties on the model's parameters (like L2 regularization) or its structure during training (like Dropout) to reduce its complexity and force it to learn more robust, generalizable patterns. [6, 11]

Question 137: Which activation function is most commonly used in the hidden layers of modern deep CNNs?

Softmax
ReLU (Correct answer)
Tanh
Sigmoid

Correct answer: ReLU

ReLU (Rectified Linear Unit) is the dominant activation in hidden layers because it is computationally efficient and mitigates the vanishing gradient problem.

Question 138: Martha Cage, a 46-year-old woman, underwent CAPD after developing chronic glomerulonephritis-related kidney failure. Question: Ms Cage undergoes contrast-associated CT after it is revealed that she has a hernia. The patient's peritoneal cavity is filled with 2 L of dialysate that contains 100 mL of the contrast agent (Omnipaque 300). The patient should follow up after installation.

Lie in the supine position for 2 hours and then have the CT
Immediately have the CT without any wait time
Carry out normal routines for 5 hours and then have the CT
Walk about or remain active for 2 hours and then have the CT (Correct answer)

Correct answer: Walk about or remain active for 2 hours and then have the CT

After instilling a contrast agent into the peritoneal cavity for a CT scan, it is recommended for the patient to ambulate or remain active for a period, typically 1-2 hours, before the scan. This activity helps to evenly distribute the contrast agent throughout the peritoneal cavity, improving the quality and diagnostic accuracy of the CT images for detecting a hernia by ensuring optimal visualization.

Question 139: Melissa Cheng, a 62-year-old woman receiving hemodialysis, complains of constant scratching. Question: If replacing Ms Walker's dialyzers and modifying her Kt/V do not relieve her itching, the most recommended step is:

UBV phototherapy
Gabapentin
Tacrolimus ointment
Moisturizers/oil bath (Correct answer)

Correct answer: Moisturizers/oil bath

Uremic pruritus, or itching, is a common and distressing symptom in hemodialysis patients. After optimizing dialysis adequacy (Kt/V) and ruling out other causes, the initial and most conservative approach to managing itching is often topical treatment. Moisturizers and oil baths help to hydrate the skin, reduce dryness, and alleviate irritation, which can significantly reduce the severity of pruritus.

Question 140: Why does max pooling provide a degree of translation invariance in CNNs?

It rotates the feature map to align dominant orientations
It normalizes activations so that their spatial positions become irrelevant
It selects the peak activation in a region regardless of its exact position within that window (Correct answer)
It averages activations, smoothing out positional differences

Correct answer: It selects the peak activation in a region regardless of its exact position within that window

Max pooling discards the precise location of a feature within the pooling window, so small shifts in input position produce the same output, yielding local translation invariance.

Question 141: What is the primary effect of average pooling compared to max pooling in CNNs?

Increases spatial resolution of the feature map
Produces sharper feature maps by emphasizing dominant activations
Eliminates negative activations from the feature map
Smooths feature maps by computing the mean of values in each region (Correct answer)

Correct answer: Smooths feature maps by computing the mean of values in each region

Average pooling computes the mean of all values in a pooling window, resulting in smoother feature maps compared to max pooling.

Question 142: What does the CutOut augmentation technique do?

Crops the image into multiple patches
Randomly masks out a square region of the input during training (Correct answer)
Applies random color cutoffs
Removes the image background

Correct answer: Randomly masks out a square region of the input during training

CutOut randomly zeroes out a square patch in the training image, forcing the network to use context from the entire image rather than relying on a single discriminative region.

Question 143: What is the purpose of the squeeze-and-excitation (SE) block in SENet?

To merge feature maps from different layers using element-wise addition
To reduce spatial resolution by 50% between convolutional blocks
To apply group normalization across subsets of channels
To recalibrate channel-wise feature responses by modeling inter-channel dependencies (Correct answer)

Correct answer: To recalibrate channel-wise feature responses by modeling inter-channel dependencies

The SE block globally pools feature maps, learns channel importance weights via two FC layers, and scales channels accordingly — acting as channel-wise attention.

Question 144: Which non-pharmaceutical treatments may be most effective for the patient if they continue to have persistent episodes of depression while taking an SSRI for three months?

Group therapy
Cognitive behavioral therapy (Correct answer)
Psychoanalysis
Electroconvulsive therapy

Correct answer: Cognitive behavioral therapy

Cognitive Behavioral Therapy (CBT) is a highly effective non-pharmacological treatment for persistent depression, often used in conjunction with or as an alternative to medication. CBT helps patients identify and change negative thought patterns and behaviors that contribute to depression. It is a well-established, evidence-based therapy for managing depressive episodes.

Question 145: Which quantity represents the number of output feature maps produced by a convolutional layer?

Number of filters (Correct answer)
Input channel count
Filter spatial size
Stride value

Correct answer: Number of filters

Each filter produces exactly one output feature map, so the number of output channels equals the number of filters.

Question 146: When fine-tuning a pre-trained CNN, it is a common best practice to use a significantly smaller learning rate for the convolutional layers than for the newly added classifier head. What is the primary reason for this practice, often called 'differential learning rates'?

To make only small, careful adjustments to the pre-trained weights, preventing the catastrophic forgetting of valuable learned features. (Correct answer)
To force the early layers to change drastically and specialize in the features of the new dataset.
A smaller learning rate is a mandatory requirement for optimizers like Adam when applied to convolutional layers.
To ensure the new, randomly initialized classifier head learns much slower than the rest of the network.

Correct answer: To make only small, careful adjustments to the pre-trained weights, preventing the catastrophic forgetting of valuable learned features.

The weights of the pre-trained convolutional layers already contain a vast amount of useful information. A high learning rate would cause large updates, potentially destroying this information. Using a much smaller learning rate ensures that these weights are only slightly adjusted (fine-tuned) to become more relevant to the new task, preserving the core of their learned knowledge.

Question 147: A researcher is working with a standard ResNet-50 model and wants to generate a class-specific heatmap showing important image regions for a prediction. Since this architecture doesn't end with a Global Average Pooling (GAP) layer suitable for classic CAM, which popular technique can they use without retraining or modifying the model?

Principal Component Analysis (PCA) on feature maps.
Gradient-weighted Class Activation Mapping (Grad-CAM). (Correct answer)
Deconvolution (Transposed Convolution).
Layer-wise Relevance Propagation (LRP).

Correct answer: Gradient-weighted Class Activation Mapping (Grad-CAM).

Grad-CAM is a generalization of CAM designed specifically for this scenario. It overcomes the architectural limitation of requiring a GAP layer by using the gradient information flowing into the final convolutional layer. These gradients are used to weight the feature maps, indicating their importance for a specific class prediction, making it applicable to a wide range of CNN architectures like ResNet without modification.

Question 148: In a bottleneck residual block (ResNet-50+), what is the purpose of the 1×1 convolutions flanking the 3×3 layer?

To perform batch normalization without an extra layer
To add non-linearity before the skip connection
To reduce and then restore channel depth, lowering computation for the 3×3 step (Correct answer)
To apply spatial attention across the feature map

Correct answer: To reduce and then restore channel depth, lowering computation for the 3×3 step

The flanking 1×1 convolutions compress channels before the expensive 3×3 convolution and expand them back, making the block computationally efficient.

Question 149: What effect does L1 regularization have on CNN weight vectors compared to L2?

It doubles the gradient magnitude
It increases the learning rate
It produces sparse weights with many zeros (Correct answer)
It produces uniformly small weights

Correct answer: It produces sparse weights with many zeros

L1 regularization adds an absolute-value penalty that drives many weights exactly to zero, producing sparse weight vectors.

Question 150: A pretrained CNN trained on ImageNet is being adapted for satellite imagery classification. Which transfer learning strategy is MOST appropriate?

Fine-tune all layers with a small learning rate (Correct answer)
Freeze all layers and only add a new softmax output
Use the model as-is with no retraining
Train from scratch ignoring ImageNet weights

Correct answer: Fine-tune all layers with a small learning rate

Satellite imagery differs significantly from ImageNet photos, so fine-tuning all layers (with a small LR) allows the model to adapt its features.

Certified Nephrology Nurse Exam

The CNN exam, administered by the Nephrology Nursing Certification Commission (NNCC), is a computer-based test consisting of 150 questions (130 scored, 20 unscored pretest) with a 3-hour time limit. A passing standard score of 95 is required, equivalent to answering approximately 70% of scored questions correctly. Content spans five clinical areas: concepts of kidney disease, hemodialysis, peritoneal dialysis, transplant, and acute therapies, along with professional practice standards.

150

Questions

180 min

Time Limit

70%

To Pass

Checking for saved progress...

Exam Rules

You can skip questions and return to them later
Flag questions for review before submitting
No feedback shown until you submit the entire exam
Unanswered questions count as wrong — answer everything
10 pretest questions are mixed in and don't affect your score
Timer auto-submits when time runs out
Your progress is auto-saved every 30 seconds

These practice questions were written with AI tools. They are not real exam questions. Exam facts are checked against the official sources listed below. Not reviewed by a subject-matter expert. Editorial policy

Sources & references

Exam facts on this page (fees, format, dates, passing scores) are checked against these official sources; the date is our last check. Editorial policy

nncc-exam.org — Fees, retake policy, score release, test dates, score validity, exam format, passing score, time limit · verified Oct 2026