English: A diagram of a convolutional neural network (CNN) architecture. The diagram shows an input image layer, which in this case is an image of a page with text and an illustration of a rabbit, followed by convolutional and pooling layers that constitute the feature learning process, a vectorisation layer that flattens the data prior to the classification process, that consists of connected layers. The example output suggests that the illustration has a 0.2 chance of being a pig, a 0.3 chance of being a horse and a 0.7 likelihood of being a rabbit.