A convolutional neural network takes an image, for example, and processes it until it can be interpreted.
For example, imagine you have to represent the sun with an ordinary pencil and a piece of paper. It is a sunny day, and the sun shines very brightly, too brightly. You put on a special pair of very dense sunglasses. Now you can look at the sun for a few seconds. You have just applied a color reduction filter, one of the first operations of a convolutional network. Then you try to draw the sun. You draw a circle and put some gray in the middle. You have just applied an edge filter. Finally, you go over the circle several times to make it easy to recognize, reducing the image you saw progressively into a representation of ...
