关键词: 深度置信网, 神经网络, Dropout, 深度学习

Abstract:

Traditional shadow learning has a simple structure and fast algorithm but a relatively high error rate,and is easy to step into the localminimization.This article discusses a deep structure call Deep Belief Network (DBN),which is used to optimize the initial value of the traditional BP to get a better testing result.And we use the dropout skill to modify the hidden unit of BP to get a fast training speed.The experiments in the article show that using DBN and dropout to modify the BP can decrease the error rate and improve the realtimeness.

Key words: deep belief network;neural network;Dropout;deep learning