01. Assessment

If during the training of a neural network you notice that some of the nodes have very low weights and do not contribute much to the model, what approach could you take to solve this?

SOLUTION: Dropout.

If a neural network has 3 layers of sizes (2, 3, 1) and no bias units, how many weights do we have to train?

SOLUTION: 9

Which activation function is more likely to cause a vanishing gradient?

SOLUTION: Sigmoid

You have designed a CNN architecture for a classification task, and you notice that your model is overfitting. Which is most likely to reduce overfitting?

SOLUTION: Decrease the number of filters in each convolutional layer

What is the best way to ensure a CNN classifier is capable of detecting objects with various sizes and at different positions in image data?

SOLUTION: Expand the existing training and validation data through augmentation.