Rolling in the Deep Convolutional Neural Networks

Abstract

Over the past years, convolutional neural networks (CNNs) have achieved remarkable success in deep learning. The performance of CNN-based models has caused major advances in a wide range of tasks from computer vision to natural language processing. However, the exposition of the theoretical calculations behind the convolution operation is rarely emphasized. This study aims to provide better understanding the convolution operation entirely by means of diving into the theory of how backpropagation algorithm works for CNNs. In order to explain the training of CNNs clearly, the convolution operation on images is explained in detail and backpropagation in CNNs is highlighted. Besides, Labeled Faces in the Wild (LFW) dataset which is frequently used in face recognition applications is used to visualize what CNNs learn. The intermediate activations of a CNN trained on the LFW dataset are visualized to gain an insight about how CNNs perceive the world. Thus, the feature maps are interpreted visually as well, alongside the training process.