CNN - Convolutional Neural Networks Training and Optimization Questions and Answers

Question 1

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

Accepted Answer

Dropout

Answer

Batch Normalization

Answer

Adam Optimizer

Answer

Data Augmentation

Question 2

When applying transfer learning to a new image classification task with a very small and highly similar dataset compared to the original pre-trained model's dataset (e.g., ImageNet), what is the most appropriate strategy?

Accepted Answer

Freeze all convolutional layers and only train the final, newly added classification layers.

Answer

Re-train the entire network from scratch with a very high learning rate.

Answer

Unfreeze all layers and fine-tune the entire network with a moderately high learning rate.

Answer

Use only the first few convolutional layers and build a new, deeper classifier on top.

Question 3

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

Accepted Answer

Adam

Answer

Adagrad

Answer

Nesterov Accelerated Gradient

Answer

RMSprop

Question 4

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?

Accepted Answer

Batch Normalization

Answer

L2 Regularization

Answer

Learning Rate Annealing

Answer

Gradient Clipping

Question 5

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?

Accepted Answer

Cosine Annealing

Answer

Step Decay

Answer

Exponential Decay

Answer

Time-Based Decay

Question 6

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

Accepted Answer

Random vertical flipping

Answer

Slight rotation (e.g., +/- 10 degrees)

Answer

Minor translation (shifting)

Answer

Small scaling (zooming in/out)