Certified Nephrology Nurse Exam — Questions and Answers

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

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

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

It uses dilated convolutions to increase receptive field without more parameters
It replaces ReLU with sigmoid to prevent dead neurons
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 3: How does GoogLeNet reduce computational cost before applying 3x3 and 5x5 convolutions in the Inception module?

By reducing the input image resolution
By applying 1x1 convolutions as bottlenecks (Correct answer)
By using strided convolutions
By using average pooling before convolution

Correct answer: By applying 1x1 convolutions as bottlenecks

1x1 convolutions act as bottlenecks that reduce the number of input channels before more expensive 3x3 and 5x5 convolutions are applied.

Question 4: What is 'Nesterov Accelerated Gradient' (NAG) and how does it differ from standard momentum SGD?

NAG applies momentum after the gradient step, while standard momentum applies it before
NAG computes the gradient at the lookahead position (after the momentum step) rather than the current position (Correct answer)
NAG adapts momentum based on curvature information
NAG uses second-order gradient information unlike standard momentum

Correct answer: NAG computes the gradient at the lookahead position (after the momentum step) rather than the current position

NAG evaluates the gradient at the predicted future position (current weights plus momentum step) rather than the current position, providing a more informed and corrective update.

Question 5: Which of the following represents collegial communication when thinking about interdisciplinary communication?

A patient asks the nurse about occupational therapy, and the nurse replies
Over lunch, the physical therapist and nurse discuss their travel plans
The nurse reports on the patient’s condition in a team meeting (Correct answer)
A patient receives personalized guidance from the nurse regarding wound care

Correct answer: The nurse reports on the patient’s condition in a team meeting

Collegial communication in an interdisciplinary healthcare setting involves professional, respectful, and collaborative information exchange among team members. A nurse reporting on a patient's condition in a team meeting is a prime example, as it facilitates shared understanding, coordinated care planning, and informed decision-making among various healthcare professionals to ensure comprehensive patient care.

Question 6: In AlexNet, what was the purpose of Local Response Normalization (LRN)?

To replace dropout during training
To scale gradients during backpropagation
To normalize activations across neighboring feature maps for lateral inhibition (Correct answer)
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 7: Which loss function is most appropriate when training a CNN for multi-label classification where each image can belong to multiple classes?

Mean squared error over class logits
Categorical cross-entropy with softmax
Hinge loss with one-vs-all strategy
Binary cross-entropy with sigmoid applied per class (Correct answer)

Correct answer: Binary cross-entropy with sigmoid applied per class

Binary cross-entropy with a sigmoid activation per output neuron treats each class independently as a binary decision, correctly handling multi-label scenarios where multiple classes can be true simultaneously.

Question 8: Which pooling operation is most commonly used in CNNs and what does it compute?

Average pooling — computes the mean of values in the pooling window
L2 pooling — computes the Euclidean norm of values in the window
Max pooling — selects the maximum value in the pooling window (Correct answer)
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 9: 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 has no effect because BN removes the dependence on learning rate scale
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)

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

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

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

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

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 12: Which statement about Dropout during inference (test time) in a CNN is correct?

Dropout rate is doubled at test time
Dropout is applied with the same rate as training
Dropout is replaced by Batch Normalization
Dropout is disabled and weights are scaled by the keep probability (Correct answer)

Correct answer: Dropout is disabled and weights are scaled by the keep probability

At inference, Dropout is turned off and weights are scaled by the keep probability (or equivalently, outputs are scaled at training) to maintain expected activation magnitudes.

Question 13: Why are deeper convolutional layers in a CNN said to have larger 'receptive fields'?

They use larger filters than early layers
Their filters are applied with larger strides
Each neuron integrates information from an increasingly larger region of the original input (Correct answer)
They have more channels

Correct answer: Each neuron integrates information from an increasingly larger region of the original input

As feature maps are stacked, each subsequent neuron indirectly covers a larger spatial region of the original input, giving it a larger effective receptive field.

Question 14: What is Panoptic Segmentation?

Segmentation applied to panoramic images only
Segmentation applied exclusively to medical images
A unified task that combines semantic segmentation (stuff) and instance segmentation (things) into a single cohesive map (Correct answer)
A multi-view segmentation approach

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

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

Question 15: What problem do residual connections in ResNet primarily solve?

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

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 16: Why is batch normalization sometimes problematic when fine-tuning a pretrained CNN on a small dataset?

Batch normalization layers cannot be frozen
It increases the number of trainable parameters significantly
Small batch statistics diverge from pretrained population statistics, causing instability (Correct answer)
It prevents gradients from flowing to earlier layers

Correct answer: Small batch statistics diverge from pretrained population statistics, causing instability

With small batches from a new domain, batch norm's running statistics become unreliable, often degrading fine-tuning performance.

Question 17: Which technique adds Gaussian noise to the gradients during CNN training to help escape sharp local minima?

Weight decay
Gradient clipping
Stochastic gradient noise (Correct answer)
Batch normalization

Correct answer: Stochastic gradient noise

Stochastic gradient noise injects Gaussian noise into gradients during optimization, helping the model escape sharp local minima and find flatter, more generalizable optima.

Question 18: 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?

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

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 19: What is the main trade-off when increasing the number of anchor boxes per location in a detector?

Better generalization but worse localization
Faster training but lower mAP
Lower recall but faster inference
Higher recall but increased computational cost and memory (Correct answer)

Correct answer: Higher recall but increased computational cost and memory

More anchors improve coverage of object shapes and sizes (higher recall) but increase the number of predictions to process, raising computation and memory cost.

Question 20: 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 21: What is the primary purpose of a pooling layer in a Convolutional Neural Network?

To introduce non-linearity into the network.
To perform feature extraction by applying filters.
To increase the number of parameters in the model.
To reduce the spatial dimensions of the feature maps. (Correct answer)

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

Pooling layers, such as max pooling or average pooling, are used to downsample the feature maps, which reduces their width and height. This process helps to decrease the computational complexity, control overfitting, and make the network more invariant to small translations in the input image.

Question 22: What does 'gradient accumulation' allow during CNN training with limited GPU memory?

Caching gradients to speed up the backward pass
Using a larger effective batch size by accumulating gradients over multiple mini-batches before updating (Correct answer)
Combining gradients from multiple models for ensemble training
Storing gradients across epochs to avoid recomputation

Correct answer: Using a larger effective batch size by accumulating gradients over multiple mini-batches before updating

Gradient accumulation sums gradients over several small mini-batches before performing a weight update, simulating a larger batch size without requiring additional GPU memory.

Question 23: What are dilated (atrous) convolutions and why are they used in semantic segmentation?

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

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 24: Which component of Faster R-CNN is shared between the RPN and the detection head?

The RoI pooling layer
The classification layer
The bounding box regression layer
The convolutional feature extractor (backbone) (Correct answer)

Correct answer: The convolutional feature extractor (backbone)

Both the RPN and the detection head use the same convolutional backbone features, making computation efficient.

Question 25: 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?

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

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 26: 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?

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

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

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

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

Mixup
Label smoothing (Correct answer)
Knowledge distillation
Temperature scaling

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

It averages across spatial dimensions to produce a single value per feature map, replacing dense layers (Correct answer)
It normalizes activations globally to prevent covariate shift
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 30: During CNN training, which regularization method randomly drops entire feature maps rather than individual neurons?

DropBlock (Correct answer)
Weight decay
SpatialDropout
Dropout

Correct answer: DropBlock

DropBlock drops contiguous regions of feature maps, which is more effective for CNNs than standard dropout because adjacent units in feature maps tend to be correlated.

Question 31: Which CNN training phenomenon occurs when a model performs well on training data but poorly on unseen test data?

Underfitting
Covariate shift
Overfitting (Correct answer)
Gradient saturation

Correct answer: Overfitting

Overfitting occurs when the model memorizes training data patterns rather than learning generalizable features, resulting in high training accuracy but poor test performance.

Question 32: What does the ColorJitter augmentation randomly alter in a training image?

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

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

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

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

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

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

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

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 36: What is domain adaptation in the context of CNN transfer learning?

Techniques to reduce the distribution gap between source and target domains (Correct answer)
Changing the CNN architecture to match the new task
Adapting the learning rate schedule during fine-tuning
Converting image formats to match training data

Correct answer: Techniques to reduce the distribution gap between source and target domains

Domain adaptation methods minimize the statistical gap between source and target distributions so that pretrained features generalize better.

Question 37: How does max pooling contribute to a CNN's resistance to overfitting?

It adds noise to feature maps
It reduces spatial resolution, decreasing parameter count in subsequent layers (Correct answer)
It applies L2 penalties to filters
It randomly drops feature map values

Correct answer: It reduces spatial resolution, decreasing parameter count in subsequent layers

Max pooling downsamples feature maps, which reduces the number of inputs to subsequent layers and thus the total number of learned parameters.

Question 38: In the context of a convolutional operation, what does the 'stride' parameter define?

The size of the pooling window used for downsampling.
The number of filters applied to the input volume.
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 39: Why is it problematic to use the test set to choose the best regularization hyperparameters in a CNN experiment?

It reduces the number of available training samples
It prevents overfitting on training data
It causes information leakage, making the model appear to generalize better than it truly does (Correct answer)
It makes training slower

Correct answer: It causes information leakage, making the model appear to generalize better than it truly does

Using the test set for hyperparameter selection causes data leakage, resulting in over-optimistic performance estimates that do not reflect true generalization.

Question 40: 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 41: Which regularization technique randomly zeroes out feature maps during training in CNNs rather than individual neurons?

Batch Normalization
Weight decay
Spatial Dropout (Correct answer)
L2 regularization

Correct answer: Spatial Dropout

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

Question 42: What distinguishes a ResNet 'basic block' from a 'bottleneck block'?

Basic blocks use 1x1 convolutions; bottleneck blocks use 3x3
Basic blocks have two 3x3 convolutions; bottleneck blocks have a 1x1-3x3-1x1 sequence (Correct answer)
Basic blocks are used in ResNet-50+; bottleneck blocks in ResNet-18/34
Basic blocks include batch normalization; bottleneck blocks do not

Correct answer: Basic blocks have two 3x3 convolutions; bottleneck blocks have a 1x1-3x3-1x1 sequence

Basic blocks (used in ResNet-18/34) stack two 3x3 convolutions, while bottleneck blocks (ResNet-50+) use a 1x1→3x3→1x1 pattern to reduce parameters.

Question 43: A CNN trained on 10,000 images achieves 99% training accuracy but only 62% validation accuracy. Which symptom does this describe?

Underfitting
High bias
Overfitting (Correct answer)
Gradient vanishing

Correct answer: Overfitting

A large gap between training accuracy (99%) and validation accuracy (62%) is the classic symptom of overfitting.

Question 44: What is the output depth (number of channels) when 128 filters are applied to a 64-channel input?

192
8192
128 (Correct answer)
64

Correct answer: 128

The output depth always equals the number of filters, regardless of the input channel count.

Question 45: 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.

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

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

To enforce weight sharing across different resolution branches
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

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

To introduce non-linearity, allowing the network to learn more complex patterns. (Correct answer)
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 convert the output into a probability distribution for classification.

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 48: During inference, how does batch normalization behave differently compared to training?

It applies normalization only to the first and last layers
It uses a larger batch to compute more accurate statistics
It disables all normalization and passes activations unchanged
It uses population statistics (running mean and variance) instead of batch statistics (Correct answer)

Correct answer: It uses population statistics (running mean and variance) instead of batch statistics

During inference, batch normalization uses fixed population statistics (running mean and variance accumulated during training) rather than computing batch statistics, ensuring consistent outputs for single samples.

Question 49: What does 'dilation' (atrous convolution) add to a standard convolution?

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)
A skip connection that bypasses the current layer

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

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

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

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

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 52: What is label smoothing in CNN training and what problem does it address?

Augmenting labels with noise to prevent overfitting to overconfident predictions (Correct answer)
Smoothing the loss curve with exponential moving average
Randomly swapping class labels during training
Applying softmax temperature scaling at test time

Correct answer: Augmenting labels with noise to prevent overfitting to overconfident predictions

Label smoothing replaces hard 0/1 targets with soft values (e.g., 0.9/0.1), preventing the model from becoming overconfident and improving generalization.

Question 53: What is 'catastrophic forgetting' in CNN training and which approach helps mitigate it?

Loss of training data due to hardware failure; mitigated by checkpointing
The tendency of a neural network to forget previously learned tasks when trained on new data; mitigated by Elastic Weight Consolidation (EWC) (Correct answer)
Gradient explosion causing weight overflow; mitigated by clipping
Forgetting to normalize inputs; mitigated by batch normalization

Correct answer: The tendency of a neural network to forget previously learned tasks when trained on new data; mitigated by Elastic Weight Consolidation (EWC)

Catastrophic forgetting occurs in continual learning when training on new tasks overwrites weights critical for old tasks; EWC adds a regularization term that penalizes changes to important weights.

Question 54: During CNN training, what is the purpose of the 'learning rate warmup' phase?

To reduce batch size at the start of training
To gradually increase the learning rate from near-zero before using the main schedule (Correct answer)
To start with a large learning rate for fast initial progress
To freeze early layers while training later layers first

Correct answer: To gradually increase the learning rate from near-zero before using the main schedule

Warmup slowly increases the learning rate from a very small value, stabilizing early training when weights and gradients are poorly scaled before the main learning rate schedule begins.

Question 55: 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 have a Global Average Pooling (GAP) layer followed by a dense output layer. (Correct answer)
The network must not contain any pooling layers.
The network must use only 3x3 convolutional filters.
The network must be trained using a sigmoid activation function in all layers.

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 56: In what year did ResNet win the ImageNet Large Scale Visual Recognition Challenge (ILSVRC)?

2014
2015 (Correct answer)
2013
2012

Correct answer: 2015

ResNet won ILSVRC 2015 with a top-5 error of 3.57%, surpassing human-level performance on the ImageNet classification task.

Question 57: What is the effect of applying batch normalization after a convolutional layer before the activation function?

Doubles the number of parameters in the layer
Removes the need for filters entirely
Replaces the bias term with a learned mean
Normalizes activations to have zero mean and unit variance, stabilizing training (Correct answer)

Correct answer: Normalizes activations to have zero mean and unit variance, stabilizing training

Batch normalization standardizes pre-activation values across the mini-batch, reducing internal covariate shift and enabling higher learning rates.

Question 58: 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?

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

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 59: 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 ensure the new, randomly initialized classifier head learns much slower than the rest of the network.
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.

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

It increases spatial resolution
It changes the number of channels without altering spatial dimensions (Correct answer)
It acts as a pooling operation
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 61: Which architecture first demonstrated that network depth beyond 20 layers could be effectively trained?

AlexNet
ResNet (Correct answer)
SqueezeNet
VGGNet

Correct answer: ResNet

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

Question 62: What is the 'bias-variance tradeoff' as it applies to CNN design?

Adding more layers always reduces both bias and variance
Larger datasets always reduce both bias and variance equally
Increasing model capacity reduces bias but can increase variance (overfitting) (Correct answer)
Regularization increases both bias and variance

Correct answer: Increasing model capacity reduces bias but can increase variance (overfitting)

Larger CNN capacity reduces training error (bias) but increases sensitivity to training data fluctuations (variance), risking overfitting.

Question 63: What is 'cyclical learning rates' (CLR) in CNN optimization?

Alternating between SGD and Adam optimizers
Decreasing the learning rate exponentially across training
Using different learning rates for each layer
Oscillating the learning rate between a minimum and maximum bound in cycles (Correct answer)

Correct answer: Oscillating the learning rate between a minimum and maximum bound in cycles

CLR varies the learning rate cyclically between a lower and upper bound, allowing the optimizer to periodically escape saddle points and explore the loss surface more effectively.

Question 64: 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 65: What is the role of the activation function applied after a convolutional layer?

Reduces the spatial dimensions of the feature map
Introduces non-linearity so the network can learn complex feature hierarchies (Correct answer)
Converts the feature map to a scalar
Normalizes the weights of the filter

Correct answer: Introduces non-linearity so the network can learn complex feature hierarchies

Without non-linear activations, stacking convolutional layers would collapse to a single linear operation, losing representational power.

Question 66: Which statement correctly describes the GELU (Gaussian Error Linear Unit) activation function?

GELU clips all inputs to the range [-3, 3] using Gaussian thresholding
GELU is identical to ReLU but with added Gaussian noise during training
GELU is a piecewise linear function with a fixed negative slope for x < 0
GELU weights inputs by their Gaussian cumulative distribution, producing a smooth non-monotonic shape near zero (Correct answer)

Correct answer: GELU weights inputs by their Gaussian cumulative distribution, producing a smooth non-monotonic shape near zero

GELU multiplies the input by Φ(x), the standard Gaussian CDF, creating a smooth curve that gently gates activations and is used in models like BERT and GPT.

Question 67: What does 'test-time augmentation' (TTA) do to improve CNN prediction performance?

Applies multiple augmentations to test images and averages the predictions (Correct answer)
Increases model capacity before inference
Fine-tunes the model briefly on test data
Augments the training set with extra images at test time

Correct answer: Applies multiple augmentations to test images and averages the predictions

TTA generates multiple augmented versions of each test image, passes them through the model, and averages the predictions to reduce variance and improve accuracy.

Question 68: In the context of CNNs, what does 'weight sharing' mean and why is it important?

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

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

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

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

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)
They are dynamically generated for each image to perfectly match the ground-truth objects before training begins.
They are used exclusively to calculate the Intersection over Union (IoU) for the final evaluation metric.
They are the final, perfectly localized bounding boxes output by the model.

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 71: 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?

Random, noisy, and uninterpretable patterns.
Gabor-like filters detecting edges at various orientations and color blobs. (Correct answer)
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 72: A data scientist is training a CNN and wants to implement a learning rate schedule that starts with a relatively high learning rate and then smoothly decreases it following the shape of a cosine curve, potentially with periodic restarts. What is this scheduling strategy called?

Cosine Annealing (Correct answer)
Exponential Decay
Step Decay
Time-Based Decay

Correct answer: Cosine Annealing

Cosine Annealing is a learning rate schedule where the learning rate is adjusted according to the cosine function. It starts with a higher value and smoothly 'anneals' or decreases to a minimum value. [26] This strategy can be very effective, especially when used with 'warm restarts,' where the learning rate is periodically reset to its initial high value, which can help the model escape poor local minima. [26]

Question 73: 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?

Underfitting; increase model complexity by adding more layers.
Overfitting; apply Dropout to the fully connected layers. (Correct answer)
Vanishing gradients; switch to a different activation function like Leaky ReLU.
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 74: What is the primary goal of applying t-SNE to CNN feature vectors extracted from an intermediate layer?

To reduce the number of filters in the layer
To convert feature maps into saliency maps
To measure filter redundancy during training
To visualize high-dimensional feature space by projecting similar activations close together in 2D (Correct answer)

Correct answer: To visualize high-dimensional feature space by projecting similar activations close together in 2D

t-SNE projects high-dimensional CNN feature vectors into 2D, clustering semantically similar images together, revealing the structure of learned representations.

Question 75: Which classic CNN was specifically designed to fit on embedded systems with a model size under 0.5MB using 'fire modules'?

ShuffleNet
SqueezeNet (Correct answer)
MobileNet
EfficientNet-B0

Correct answer: SqueezeNet

SqueezeNet (2016) used 'fire modules' with squeeze and expand layers to achieve AlexNet-level accuracy at less than 0.5MB, targeting embedded deployment.

Question 76: What is the 'dead ReLU' problem during CNN training?

Neurons with negative pre-activation permanently output zero and stop learning (Correct answer)
ReLU causes the loss to become non-differentiable
ReLU causes exploding gradients in deep networks
ReLU activation leads to sparse but unreliable features

Correct answer: Neurons with negative pre-activation permanently output zero and stop learning

Dead ReLUs occur when a neuron's input is always negative, causing it to output zero and receive zero gradient, effectively removing it from learning permanently.

Question 77: Which technique involves training a lightweight student model to mimic a larger pretrained teacher model?

Model pruning
Knowledge distillation (Correct answer)
Multi-task learning
Progressive fine-tuning

Correct answer: Knowledge distillation

Knowledge distillation trains a compact student to replicate the teacher's soft outputs, transferring knowledge to a smaller deployable model.

Question 78: When freezing layers during transfer learning in Keras/TensorFlow, which attribute is set to False?

layer.active
layer.trainable (Correct answer)
layer.requires_grad
layer.frozen

Correct answer: layer.trainable

Setting layer.trainable = False in Keras prevents weight updates for that layer during training.

Question 79: 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)
American Association of Kidney Patients
National Kidney Foundation
National Organization for Renal Disease

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 80: What is spatial dropout (also called 2D dropout) and when is it used?

Randomly masking contiguous rectangular regions of the input image
Applying dropout only in the spatial height/width dimensions but keeping all channels
Dropping activations in a structured grid pattern across the feature map
Dropping entire feature maps (channels) rather than individual activations in CNNs (Correct answer)

Correct answer: Dropping entire feature maps (channels) rather than individual activations in CNNs

Spatial dropout drops entire feature maps (channels) at once rather than individual elements, which is more effective for CNNs because adjacent pixels in a feature map are highly correlated.

Question 81: Which method synthesizes an input image from scratch to maximize a neuron's activation, rather than searching the training set?

Activation maximization (deep dream / feature visualization) (Correct answer)
Dropout visualization
Feature map subtraction
Weight histogram analysis

Correct answer: Activation maximization (deep dream / feature visualization)

Activation maximization iteratively updates a random input image via gradient ascent to maximize a target neuron's response, revealing the ideal stimulus.

Question 82: What does 'feature extraction' mode mean in transfer learning?

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

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

Varies widely
Increases
Remains consistent
Decreases (Correct answer)

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 84: Feature maps from different channels in the same convolutional layer represent what?

Separate images in the batch
Different color channels of the output
Different learned detectors applied to the same spatial locations (Correct answer)
The same filter applied at different strides

Correct answer: Different learned detectors applied to the same spatial locations

Each channel in a convolutional layer's output corresponds to a different learned filter, so channels capture different types of patterns at the same spatial resolution.

Question 85: In a fully convolutional network (FCN), what replaces the fully connected layers to enable pixel-wise predictions?

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

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 86: 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 reduce the number of parameters in the network through downsampling.
To apply a set of learnable filters to the input data to create feature maps. (Correct answer)

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 87: In a CNN, what does 'stride' control?

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

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 88: 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. <br> 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:

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

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

Augmenting the test dataset permanently
Applying multiple augmentations to test images and averaging predictions to improve accuracy (Correct answer)
Speeding up inference time
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 90: 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?

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

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 91: 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?

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

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 92: What is the goal of semantic segmentation in computer vision?

Assigning a class label to every pixel in an image (Correct answer)
Detecting bounding boxes around objects
Identifying unique instances of each object
Generating captions for images

Correct answer: Assigning a class label to every pixel in an image

Semantic segmentation classifies each pixel into a predefined category, producing a dense prediction map that delineates different regions of the image.

Question 93: What loss function is most commonly used as the primary training objective in semantic segmentation CNNs?

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

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 94: What is the purpose of using a lower learning rate for earlier (pretrained) layers compared to later layers during fine-tuning?

To speed up convergence of the whole network
To prevent overfitting the validation set
To preserve general low-level features while adapting high-level ones (Correct answer)
To reduce memory usage during backpropagation

Correct answer: To preserve general low-level features while adapting high-level ones

Lower learning rates in early layers preserve generalizable edge/texture detectors, while higher rates in later layers adapt task-specific representations.

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

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

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

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

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 97: What is 'early stopping' in CNN training and what metric is typically monitored?

Stopping training after a fixed number of gradient updates
Halting training when validation loss stops improving for a set number of epochs (Correct answer)
Stopping when training loss reaches zero, monitored per batch
Terminating training when learning rate falls below a threshold

Correct answer: Halting training when validation loss stops improving for a set number of epochs

Early stopping halts training when the validation loss (or other metric) fails to improve for a specified patience period, preventing overfitting by avoiding unnecessary epochs.

Question 98: 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 99: Why does soft-NMS outperform standard NMS in crowded scene detection?

It uses a learned threshold instead of a fixed IoU cutoff
It removes all overlapping boxes regardless of score
It decays scores of overlapping boxes rather than eliminating them (Correct answer)
It applies NMS only to the highest confidence class

Correct answer: It decays scores of overlapping boxes rather than eliminating them

Soft-NMS reduces suppressed boxes' scores by a continuous function of overlap instead of hard removal, preserving detections of nearby objects.

Question 100: Which activation function did AlexNet popularize as an alternative to sigmoid and tanh?

ReLU (Correct answer)
Leaky ReLU
ELU
Swish

Correct answer: ReLU

AlexNet popularized ReLU (Rectified Linear Unit), which trains faster than sigmoid/tanh and mitigates the vanishing gradient problem.

Question 101: In a depthwise separable convolution, what does the depthwise step do?

Combines all channels into one output
Applies one filter across all channels
Applies a separate filter to each input channel independently (Correct answer)
Performs 1×1 convolutions only

Correct answer: Applies a separate filter to each input channel independently

The depthwise step convolves each input channel with its own dedicated spatial filter, keeping channels separate.

Question 102: In EfficientNet, what is 'compound scaling' and what does it scale jointly?

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

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 103: 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)
Instance segmentation works only on videos
Semantic segmentation requires depth data

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 104: What is a 'projection shortcut' in ResNet, as opposed to an 'identity shortcut'?

A shortcut that applies batch normalization before addition
A shortcut that uses a 1x1 convolution to match dimensions when channel sizes change (Correct answer)
A shortcut that averages input and output before addition
A shortcut that skips two blocks instead of one

Correct answer: A shortcut that uses a 1x1 convolution to match dimensions when channel sizes change

A projection shortcut uses a 1x1 convolution (with stride) to match the spatial and channel dimensions when the skip connection would otherwise have a size mismatch.

Question 105: What does AutoAugment do in the context of CNN training?

Automatically adjusts learning rate
Generates new architectures automatically
Searches for an optimal augmentation policy using reinforcement learning (Correct answer)
Automatically selects the best optimizer

Correct answer: Searches for an optimal augmentation policy using reinforcement learning

AutoAugment formulates the augmentation policy search as a reinforcement learning problem, where the controller learns which transformations and magnitudes maximize validation accuracy.

Question 106: Which layer type in a CNN is responsible for introducing non-linearity?

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

Correct answer: Activation layer

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

Question 107: What role does Batch Normalization play in CNN training?

It normalizes layer inputs per mini-batch, stabilizing and accelerating training (Correct answer)
It clips gradient values to prevent exploding gradients
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 108: In a bottleneck residual block (ResNet-50+), what is the purpose of the 1×1 convolutions flanking the 3×3 layer?

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

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 109: During the forward pass, what is the bias term in a convolutional layer added to?

The filter weights before convolution
Each output feature map value (one bias per filter) (Correct answer)
The loss function directly
Each input pixel

Correct answer: Each output feature map value (one bias per filter)

One scalar bias per filter is added to every spatial position in that filter's output feature map.

Question 110: 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.
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.
Freeze all convolutional layers and train only a new, randomly initialized classifier head. (Correct answer)

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 111: What is the DeepLab v3+ architecture's improvement over earlier DeepLab versions?

It removes all dilated convolutions
It replaces the backbone with a transformer
It uses recurrent layers instead of convolutions
It adds a decoder module that refines segmentation boundaries by combining low-level encoder features with the ASPP output (Correct answer)

Correct answer: It adds a decoder module that refines segmentation boundaries by combining low-level encoder features with the ASPP output

DeepLab v3+ introduces a simple but effective decoder that upsamples the ASPP output and concatenates it with low-level features from the encoder, sharpening object boundaries compared to simple bilinear upsampling.

Question 112: During CNN training, which data augmentation technique generates new training samples by combining two images and their labels linearly?

Cutout
Random Erasing
CutMix
Mixup (Correct answer)

Correct answer: Mixup

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

Question 113: How does grouped convolution (used in ResNeXt) reduce computational cost compared to standard convolution?

It removes all bias terms
It splits input channels into groups and applies independent filters per group, reducing multiplications (Correct answer)
It uses stride=2 automatically
It applies filters only to the border pixels

Correct answer: It splits input channels into groups and applies independent filters per group, reducing multiplications

By restricting each filter to convolve with only a subset of input channels (one group), grouped convolution reduces FLOPs by the group factor.

Question 114: In CNN regularization, what is 'stochastic depth' and how does it reduce overfitting in deep networks?

Applying variable Dropout rates to each layer
Gradually increasing the number of layers during training
Randomly shortcircuiting (skipping) entire residual blocks during training (Correct answer)
Shrinking the depth of the network at test time

Correct answer: Randomly shortcircuiting (skipping) entire residual blocks during training

Stochastic depth randomly bypasses entire residual layers during training, effectively training an ensemble of networks with different depths.

Question 115: Which popular pretrained CNN architecture introduced depthwise separable convolutions, making it efficient for transfer learning on mobile devices?

VGG-16
AlexNet
MobileNet (Correct answer)
ResNet-50

Correct answer: MobileNet

MobileNet uses depthwise separable convolutions to dramatically reduce computation, making it ideal for mobile and embedded transfer learning.

Question 116: What distinguishes the ELU (Exponential Linear Unit) activation from ReLU?

ELU clips activations at a fixed maximum value to prevent explosion
ELU outputs negative values for negative inputs using an exponential, giving non-zero mean activations (Correct answer)
ELU applies a sigmoid curve across all input values
ELU uses a linear function for all positive inputs and zero for negatives

Correct answer: ELU outputs negative values for negative inputs using an exponential, giving non-zero mean activations

ELU uses an exponential decay for negative inputs, pushing mean activations closer to zero and speeding up learning compared to ReLU.

Question 117: Which of the following is NOT a common technique used to combat overfitting in a CNN?

Dropout.
Data Augmentation.
L2 Regularization (Weight Decay).
Increasing the number of epochs indefinitely. (Correct answer)

Correct answer: Increasing the number of epochs indefinitely.

Increasing the number of epochs indefinitely is likely to cause overfitting, not prevent it. As a model trains for longer, it has more opportunities to memorize the noise and specific details of the training data. [24] Data augmentation, Dropout, and L2 regularization are all standard and effective techniques used to reduce overfitting and improve a model's generalization capabilities. [12, 20]

Question 118: What is 'task-specific fine-tuning' in contrast to 'feature extraction' transfer learning?

Extracting features specific to the source task
Using task-specific data only for augmentation
Training only the softmax layer on the new task
Updating pretrained weights (some or all) for the new task (Correct answer)

Correct answer: Updating pretrained weights (some or all) for the new task

Task-specific fine-tuning allows pretrained weights to be updated via backpropagation on the new task, unlike feature extraction which keeps them frozen.

Question 119: What distinguishes a 'same' padding strategy from a 'valid' padding strategy in convolutional layers?

Same padding is only used in pooling; valid padding applies to convolutions
Same padding doubles the input size; valid padding halves it
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)

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 120: How does increasing network depth in VGGNet (from VGG-11 to VGG-19) primarily affect training?

Training becomes faster due to more gradient paths
Deeper models are harder to train and may plateau or degrade without careful initialization (Correct answer)
Training accuracy improves monotonically without any downside
The additional layers are skipped automatically via gating

Correct answer: Deeper models are harder to train and may plateau or degrade without careful initialization

Deeper VGGNet variants face greater optimization difficulty due to vanishing gradients, requiring careful initialization; VGG-19 offers only marginal gains over VGG-16.

Question 121: What is the purpose of the squeeze-and-excitation (SE) block in SENet?

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

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

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

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 123: In CNN optimization, what does 'weight decay' correspond to in terms of regularization?

Dropout on convolutional filters
Elastic net regularization
L1 regularization on weights
L2 regularization on weights (Correct answer)

Correct answer: L2 regularization on weights

Weight decay adds an L2 penalty on the magnitude of weights to the loss, which penalizes large weights and encourages the model to use smaller, more distributed weights.

Question 124: In a CNN, early stopping halts training when which condition is met?

Training loss reaches zero
Learning rate becomes very small
Validation loss stops improving or starts increasing (Correct answer)
All weights converge to the same value

Correct answer: Validation loss stops improving or starts increasing

Early stopping monitors validation loss and terminates training when it plateaus or increases, indicating the model is beginning to overfit.

Question 125: Which of the following statements about acute renal failure would be judged to be the most accurate?

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

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 126: Which augmentation technique randomly flips an image along its vertical axis?

Random rotation
Horizontal flip (Correct answer)
Random crop
Vertical flip

Correct answer: Horizontal flip

A horizontal flip mirrors an image left-to-right along the vertical axis, creating a natural augmentation for many image classification tasks.

Question 127: Which backbone architecture is commonly used in modern object detectors like Faster R-CNN and RetinaNet?

LeNet-5
VGG-7
ResNet with FPN (Correct answer)
AlexNet

Correct answer: ResNet with FPN

ResNet combined with a Feature Pyramid Network is a widely used backbone for object detection due to its strong multi-scale feature representation.

Question 128: How does a transposed convolution (sometimes called deconvolution) differ from a standard convolution in terms of spatial output?

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

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 129: When fine-tuning only the last few layers of a pretrained CNN, what is the main concern if you use a very high learning rate?

Increased inference time
Overfitting the training data
Catastrophic forgetting of pretrained features (Correct answer)
Underfitting the new dataset

Correct answer: Catastrophic forgetting of pretrained features

A high learning rate can overwrite the valuable pretrained weights through catastrophic forgetting, destroying learned representations.

Question 130: 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 131: What is the key structural unit introduced by GoogLeNet (Inception v1)?

Depthwise separable convolution
Inception module (Correct answer)
Dense block
Residual block

Correct answer: Inception module

GoogLeNet introduced the Inception module, which applies 1x1, 3x3, and 5x5 convolutions in parallel and concatenates their outputs.

Question 132: 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?

R-CNN, because it uses an external selective search algorithm that is computationally efficient.
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)

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 133: LeNet-5 uses which type of pooling in its subsampling layers?

Average pooling (Correct answer)
Max pooling
Fractional pooling
Global average pooling

Correct answer: Average pooling

LeNet-5 uses average pooling (called 'subsampling') in its pooling layers, which was the standard before max pooling became dominant.

Question 134: What is the purpose of transposed convolutions (deconvolutions) in segmentation networks?

To learn to upsample feature maps back to a higher spatial resolution (Correct answer)
To transpose the weight matrix of convolution layers
To apply convolutions in the reverse order
To reduce the number of feature map channels

Correct answer: To learn to upsample feature maps back to a higher spatial resolution

Transposed convolutions perform a learnable upsampling by inserting zeros between input values and then applying a convolution, allowing the network to recover spatial resolution lost during downsampling.

Question 135: Why does max pooling provide a degree of translation invariance in CNNs?

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

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

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

Correct answer: torchvision.transforms

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

Question 137: A data scientist wants to understand which specific pixels in an input image are most influential in causing a CNN to make a particular classification decision (e.g., classifying an image as a 'dog'). Which visualization technique would be most appropriate for this purpose?

Activation Maximization.
t-SNE projection of the final feature vector.
Saliency Maps (or Gradient-based Attribution). (Correct answer)
Visualizing the filter weights directly.

Correct answer: Saliency Maps (or Gradient-based Attribution).

Saliency maps are designed to solve this exact problem. They work by computing the gradient of the output class score with respect to the input image pixels. The magnitude of the gradient for each pixel indicates how much a small change in that pixel's intensity would affect the class score, thus highlighting the most influential pixels for that specific classification decision.

Question 138: In DenseNet, how does each layer receive its input?

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

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 139: What is the primary effect of L1 regularization on the weights of a CNN?

It normalizes the activations within each layer to have a mean of zero and a standard deviation of one.
It encourages some weights to become exactly zero, leading to a sparse model. (Correct answer)
It encourages all weights to become smaller and more evenly distributed.
It has no direct effect on the weights but prunes entire network channels.

Correct answer: It encourages some weights to become exactly zero, leading to a sparse model.

L1 regularization adds a penalty to the loss function proportional to the absolute value of the weights. [12] This has the effect of pushing the weights of less important features towards exactly zero, a process that results in a 'sparse' model where many weights are zero. [8, 9, 19] This can also be seen as a form of automatic feature selection.

Question 140: What role does Dice Loss play in training semantic segmentation CNNs, particularly on imbalanced datasets?

It penalizes large weight values for regularization
It directly optimizes the overlap between predicted and ground-truth masks, making it robust to class imbalance (Correct answer)
It measures the entropy of predicted probabilities
It penalizes misclassified background pixels

Correct answer: It directly optimizes the overlap between predicted and ground-truth masks, making it robust to class imbalance

Dice Loss is derived from the Dice coefficient (2×|A∩B|/(|A|+|B|)) and directly maximizes mask overlap, giving equal weight to small foreground classes that would otherwise be dominated by the large background in cross-entropy loss.

Question 141: Which of the following best describes the 'neck' component in modern object detection architectures like YOLOv4?

The input preprocessing pipeline
The loss computation layer
Feature aggregation module between backbone and detection head (Correct answer)
The final classification head

Correct answer: Feature aggregation module between backbone and detection head

The neck (e.g., PANet, FPN) aggregates and mixes features from different backbone stages before passing them to the detection head.

Question 142: What pooling strategy does GoogLeNet use at the end of the network instead of fully connected layers?

Average pooling (Correct answer)
Max pooling
Adaptive average pooling
Fractional max pooling

Correct answer: Average pooling

GoogLeNet uses global average pooling before the final classifier, drastically reducing parameters compared to flattening into large fully connected layers.

Question 143: How does dropout act as a form of regularization?

By reducing the number of parameters in the network permanently
By penalizing large weight values via an L2 term in the loss function
By increasing the effective learning rate to escape sharp minima
By forcing the network to learn robust features not dependent on specific co-adaptations (Correct answer)

Correct answer: By forcing the network to learn robust features not dependent on specific co-adaptations

Dropout prevents co-adaptation of neurons by randomly removing them, forcing each neuron to learn useful features independently, which improves generalization.

Question 144: What filter size does VGGNet use exclusively in its convolutional layers?

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

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 145: Which pretrained model is known for its 'inception modules' that process features at multiple scales simultaneously?

SqueezeNet
DenseNet
VGG-19
GoogLeNet (Inception) (Correct answer)

Correct answer: GoogLeNet (Inception)

GoogLeNet introduced inception modules that apply convolutions of different kernel sizes in parallel, capturing multi-scale features.

Question 146: What is the primary purpose of data augmentation in CNN training?

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

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 147: A CNN is being designed to classify images where the most prominent feature (e.g., a bright edge) in a local region is the most important for classification. Which pooling strategy would be most appropriate?

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

Correct answer: Max Pooling

Max pooling selects the maximum value from each patch of the feature map. This is particularly effective at capturing the most prominent or intense features, such as bright edges or corners, while discarding less relevant information.

Question 148: What was the key innovation in the Faster R-CNN architecture that distinguished it from its predecessor, Fast R-CNN?

The use of a deeper backbone network like VGG-16 for feature extraction.
The introduction of a Region Proposal Network (RPN) to generate object proposals within the main network. (Correct answer)
The replacement of the SVM classifier with a softmax layer for object classification.
The implementation of RoI (Region of Interest) Pooling to handle inputs of different sizes.

Correct answer: The introduction of a Region Proposal Network (RPN) to generate object proposals within the main network.

The main bottleneck in Fast R-CNN was its reliance on an external, CPU-based algorithm like Selective Search to generate region proposals. The groundbreaking innovation of Faster R-CNN was the introduction of the Region Proposal Network (RPN), a fully convolutional network that is integrated into the main detection pipeline. The RPN shares convolutional features with the detection network, allowing it to generate high-quality region proposals almost for free, which made the entire object detection process significantly faster and trainable end-to-end.

Question 149: What does the peritoneal equilibration test measure?

Calculate the quantity of excess glucose in the dialysate after a 4-hour dwell has been drained
Calculate the volume of urea and creatinine filtered into the dialysate during a 4-hour dwell and the importance of glucose absorbed from the dialysate (Correct answer)
Analyze the ratio of blood urea levels to those in a 24-hour collection of dialysate that has been drained
Determine the patient’s serum urea and serum creatinine after a 4-hour dwell is drained

Correct answer: Calculate the volume of urea and creatinine filtered into the dialysate during a 4-hour dwell and the importance of glucose absorbed from the dialysate

The Peritoneal Equilibration Test (PET) is a diagnostic tool used in peritoneal dialysis to assess the transport characteristics of the patient's peritoneal membrane. It measures the rate at which solutes, such as urea and creatinine, move from the blood into the dialysate, and the rate at which glucose is absorbed from the dialysate into the blood, typically over a 4-hour dwell. This information helps tailor the optimal dialysis prescription for the patient.

Question 150: What is the 'Random Erasing' augmentation technique?

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

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.

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