Convolutional Neural Networks

Convolutional Neural Networks (CNNs)

The type of deep neural network that is most powerful in image processing tasks, such as sorting images into groups, is called a Convolutional Neural Network (CNN). CNN's consist of layers that process visual information. A CNN first takes in an input image and then passes it through these layers. There are a few different types of layers, but we'll start by learning about just a few: convolution, and fully-connected layers.

Convolutional layer

• A convolutional layer takes in an image array as input.
• A convolutional layer can be thought of as a set of image filters (which you've been learning about).
• Each filter extracts a specific kind of feature (like an edge).
• The output of a given convolutional layer is a set of feature maps, which are differently filtered versions of the input image.

Fully-connected layer

A fully-connected layer's job is to connect the input it sees to a desired form of output. As an example, say we are sorting images into two classes: day and night, you could give a fully-connected layer a set of feature maps and tell it to use a combination of these features (multiplying them, adding them, combining them, etc.) to output a prediction: whether a given image is likely taken during the "day" or "night." This output prediction is sometimes called the output layer.

Starting with Convolution

In this course, you've seen how to extract color features from an image (as in the case of a blue/green screen). In this example, it was up to you to decide what features/filters/etc. were the most useful for grouping pixel data.

This is similar to how CNN's learn to recognize patterns in images: given a training set of images, CNN's look for distinguishing features, like a distinguishing color or shape, in the images; they adjust the weights in the image filters that make up their convolutional layers, and adjust their final, fully-connected layer to accurately classify the training images (learning from any mistakes they make along the way). Building these layers from scratch, is a great way to learn the inner working of machine learning techniques!

So, in the next section, we'll learn how convolutional works and create our own convolutional kernels (also referred to as image filters).

Further learning!

As a note, CNN's are typically made of many convolutional layers and even include other processing layers whose job is to standardize data or reduce its dimensionality (for a faster network). If you are interested in learning more about CNN's and the complex layers that they can use, I recommend looking at this article as a reference.