CNN Cheat Sheet 2026

The 30 highest-yield CNN facts, distilled from real exam questions. Print it, save it as a PDF, or study it here — free, no sign-up.

1. What is 'inverted dropout' and why is it preferred in practice? → Scaling kept activations by 1/(1-p) during training so no scaling is needed at test time
2. When both batch normalization and dropout are used in the same network, what ordering is generally recommended? → Conv → Batch Norm → ReLU → Dropout (in fully connected layers)
3. What is the purpose of transposed convolutions (deconvolutions) in segmentation networks? → To learn to upsample feature maps back to a higher spatial resolution
4. Which of the following regularization techniques involves halting the training process when the model's performance on a validation set stops improving? → Early Stopping
5. What is the effect of applying Gaussian blur augmentation to CNN training images? → It simulates out-of-focus conditions, making the model robust to image blurriness
6. Which PyTorch library is most commonly used for applying data augmentation transforms to image datasets? → torchvision.transforms
7. What does AutoAugment do in the context of CNN training? → Searches for an optimal augmentation policy using reinforcement learning
8. What does a dropout layer do during training? → Randomly sets a fraction of neuron activations to zero
9. What is group normalization and what problem does it solve compared to batch normalization? → It normalizes groups of channels together, working well even with batch size of 1
10. Which of the following was a key innovation introduced in the AlexNet architecture that distinguished it from its predecessor, LeNet-5? → The use of the Rectified Linear Unit (ReLU) activation function.
11. What loss function is most commonly used as the primary training objective in semantic segmentation CNNs? → Pixel-wise Cross-Entropy Loss
12. Dialysate glucose must be heat sterilized at a low pH to → Decrease generation of glucose degradation products
13. What is spatial dropout (also called 2D dropout) and when is it used? → Dropping entire feature maps (channels) rather than individual activations in CNNs
14. Which of the following is NOT a common technique used to combat overfitting in a CNN? → Increasing the number of epochs indefinitely.
15. In the context of a convolutional operation, what does the 'stride' parameter define? → The number of pixels by which the filter slides over the input at each step.
16. Which of the following best describes the role of the convolutional layer in a CNN? → To apply a set of learnable filters to the input data to create feature maps.
17. The gradient of a substance's concentration, such as urea, during peritoneal dialysis → Decreases
18. Which of the following best describes the primary purpose of a 1x1 convolution operation in a CNN architecture? → To act as a channel-wise, fully connected layer for dimensionality reduction or expansion.
19. What are the three layers of the glomerular membrane made up of? → All of the above
20. During inference, how does batch normalization behave differently compared to training? → It uses population statistics (running mean and variance) instead of batch statistics
21. What is the 'Random Erasing' augmentation technique? → Randomly selecting a rectangle in the image and replacing it with random pixel values
22. 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.
23. In CNN training, what does the term 'augmentation policy' refer to? → A defined set of transformation operations along with their probabilities and magnitudes
24. What is the primary effect of L1 regularization on the weights of a CNN? → It encourages some weights to become exactly zero, leading to a sparse model.
25. Which of the following represents collegial communication when thinking about interdisciplinary communication? → The nurse reports on the patient’s condition in a team meeting
26. Which of the following assertions regarding renal illness is not true? → Being over the age of 40 is considered a risk factor
27. Where is batch normalization typically inserted in a convolutional block? → Before the activation function, after the convolutional layer
28. What is the effect of using a very high dropout rate (e.g., 0.9) on a CNN? → The network may underfit as too much information is lost during each forward pass
29. What risk does overly aggressive data augmentation introduce during CNN training? → It can create unrealistic training samples that hurt model performance
30. Which of the following is a defining characteristic of one-stage object detectors like SSD (Single Shot MultiBox Detector)? → They make predictions on a dense grid of locations across feature maps of multiple scales.