Different types of layers[edit]
Convolutional layer[edit]
Unlike a hand-coded convolution kernel (Sobel, Prewitt, Roberts), in a convolutional neural net, the parameters of each convolution kernel are trained by the backpropagation algorithm. There are many convolution kernels in each layer, and each kernel is replicated over the entire image with the same parameters. The function of the convolution operators is to extract different features of the input. The capacity of a neural net varies, depending on the number of layers. The first convolution layers will obtain the low-level features, like edges, lines and corners. The more layers the network has, the higher-level features it will get.