A convolutional neural network (CNN) is a  specific type of artificial neural network used in image recognition and processing that is specifically designed to process pixel data.

​

The connectivity pattern between its neurons is inspired by the organization of the visual cortex, and it works to mimic the interpretation process of human brain. The CNN model “sees” the world in a different way than we do. Its world consists of only numbers. Every image can be represented as 2-dimensional arrays of numbers, known as pixels. But the fact that they perceive images in a different way, doesn’t mean we can’t train them to recognize patterns. All we need to do is to show the CNN algorithm millions of pictures for it to be able to generalize the input and make predictions for images it has never seen before.