Deep Learning Development Review

Abstract

As a new branch of the machine learning, the nature of deep learning is to establish and simulate the neural network of human brain to analysis and learning. With the development of neural networks, the models are getting bigger and more complex, the network model is no longer a few layers, dozens or even hundreds of network models play a huge advantage. In recent years, various deep neural network models have achieved remarkable results in many fields, such as face recognition, voice recognition, natural language processing and so on. People called these large-scale neural networks 'deep learning'. This paper mainly reviews the development history of deep learning, and make a brief summary of the problems faced by deep learning at the end of the paper.