Machine Learning Algorithms

Convolutional layers

Convolutional layers are normally applied to bidimensional inputs (even though they can be used for vectors and 3D matrices) and they became particularly famous thanks to their extraordinary performance in image classification tasks. They are based on the discrete convolution of a small kernel k with a bidimensional input (which can be the output of another convolutional layer):

A layer is normally made up of n fixed-size kernels, and their values are considered as weights to learn using a back-propagation algorithm. A convolutional architecture, in most cases, starts with layers with few larger kernels (for example, 16 ...