CNN Study Guide 2026

Everything you need to pass the CNN exam in one place: the exam format, every topic to study, real practice questions with explanations, flashcards, and full-length practice tests. Free, no sign-up needed.

📋 CNN Exam Format at a Glance

150

Questions

180 min

Time Limit

70%

Passing Score

Take a Full CNN Exam Simulation →

📚 CNN Topics to Study (21)

Batch Normalization and Dropout · 7 cards Batch Normalization and Dropout · 7 cards Batch Normalization and Dropout · 7 cards Certified Nephrology Nurse · 7 cards Certified Nephrology Nurse · 7 cards Certified Nephrology Nurse · 7 cards CNN - Convolutional Neural Networks Data Augmentation Techniques Questions and Answers · 6 cards CNN - Convolutional Neural Networks Data Augmentation Techniques Questions and Answers · 6 cards CNN - Convolutional Neural Networks Data Augmentation Techniques Questions and Answers · 6 cards CNN - Convolutional Neural Networks Semantic Segmentation Questions and Answers · 6 cards CNN - Convolutional Neural Networks Semantic Segmentation Questions and Answers · 6 cards CNN - Convolutional Neural Networks Semantic Segmentation Questions and Answers · 6 cards Classic CNN Architectures · 6 cards Architecture Fundamentals · 6 cards Convolutional Layer Operations · 6 cards Object Detection Models · 6 cards Overfitting and Regularization · 6 cards Pooling and Activation Functions · 6 cards Training and Optimization · 6 cards Transfer Learning with CNNs · 6 cards Visualizing CNN Feature Maps · 6 cards

✍️ Sample CNN Questions & Answers

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

✓ 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.

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

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

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

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

✓ 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.

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

✓ 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.

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

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

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

6. What is Panoptic Segmentation?

✓ 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.

🎯 Free CNN Practice Tests

Certified Nephrology Nurse · 7 questions Batch Normalization and Dropout · 7 questions Certified Nephrology Nurse · 7 questions Certified Nephrology Nurse · 7 questions Batch Normalization and Dropout · 7 questions Batch Normalization and Dropout · 7 questions Object Detection Models · 6 questions Architecture Fundamentals · 6 questions Training and Optimization · 6 questions Pooling and Activation Functions · 6 questions

📖 CNN Guides & Articles

Your CNN Study Path

1. Learn with Flashcards → 2. Drill Practice Tests → 3. Take the Full Exam Simulation

🃏 Flashcards (132)🏆 Exam Simulation