TRAINING A CONVOLUTIONAL NEURAL NETWORK

A computer implemented methods and apparatus for use in training a convolutional neural network using a training data set. Each item of training data in the training data set comprises numerical data and a corresponding label for the respective numerical data. A method comprises, for each item of training data, converting the numerical data into a matrix, wherein elements in the matrix represent values of features in the numerical data. The method further comprises determining an arrangement for the numerical data in the matrices that decreases a similarity of matrices comprising numerical data with different labels, and/or increases a similarity of matrices comprising numerical data with the same labels, based on one or more measures of entropy.