Convolutional Neural Networks

Question 1

What is a Convolutional Neural Network?

Answer 1

A neural network used for image processing that uses a filter to transform the input image and generate a feature map.

Question 2

What is pooling?

Answer 2

A processes of aggregating, summarising, or down sampling an image into a smaller image map.

Question 3

What are two common types of pooling?

Answer 3

Max Pooling and Average Pooling

Question 4

What are some examples of model hyperparameters?

Answer 4

1. Filter Size and number of filters.
2. Padding and stride value.
3. Learning rate and dropout rate.
4. Number of epochs and batch size.
5. Activation function.
6. Number of hidden layers.
7. Number of neurons in each layer.

Question 5

What is Striding?

Answer 5

The parameter that determines how many squares or pixels the filters skip when moving across the image.

Question 6

What is Padding?

Answer 6

The process of adding extra pixels around the border of the input image and it is used to preserve the spatial dimensions of the input image.