MLG 16, 09, 2015 Introduction to convolutional neural networks by Laura Mannie Corbisier

Convolutional neural networks (CNN) are part of deep learning methods. Its main characteristic is its convolutional layer aiming at valorizing spatial information. CNN make features extraction step nearly irrelevant, reducing the need for domainspecifc prior knowledge. Like other neural networks, CNN can be computed through gradientdescent (backward propagation algorithm). One of the breakingthrough papers using backward propagationon CNN was written in 1998 by LeCun Y. , Bottou L. , Bengio Y. , Hafner P. (