Review of Deep Neural Network Based on Auto-encoder

Abstract

Deep Learning gets a new research direction of machine learning. After years of deep learning development, researchers have put forward several types of neural network built on the Auto-encoder. In this article, firstly, the origins and basic concepts of deep learning, automatic encoders, deep belief networks, and convolutional neural networks are introduced. The principle of deep neural networks based on Auto-encoders is described, and the application of hybrid neural networks in various types is introduced. Finally, the problems existing in the current stage of deep neural network based on Auto-encoders and the future prospects of it are described.