The example Create Simple Deep Learning Network for Classification shows you how to create and train an image classification network, and then use the trained network to classify a new set of images.
The trained network will be able to classify new images that are similar to the images that you used to trained the network, for example digit images.
Pretrained networks (like googlenet), which are able to classify new and different images, have been trained on over a million images and have learned rich feature representations for a wide range of images. For an example, see Train Deep Learning Network to Classify New Images.
