Title :
Deep Belief Networks and deep learning
Author :
Yuming Hua ; Junhai Guo ; Hua Zhao
Author_Institution :
Beijing Inst. of Tracking & Telecommun. Technol., Beijing, China
Abstract :
Deep Belief Network is an algorithm among deep learning. It is an effective method of solving the problems from neural network with deep layers, such as low velocity and the overfitting phenomenon in learning. In this paper, we will introduce how to process a Deep Belief Network by using Restricted Boltzmann Machines. What is more, we will combine the Deep Belief Network together with softmax classifier, and use it in the recognition of handwritten numbers.
Keywords :
Boltzmann machines; belief networks; learning (artificial intelligence); deep belief networks; deep layers; deep learning; handwritten number recognition; neural network; restricted Boltzmann machines; softmax classifier; Classification algorithms; Feature extraction; Fitting; Mathematical model; Neural networks; Training; Unsupervised learning; Deep Belief Network; Deep learning; classify Introduction;
Conference_Titel :
Intelligent Computing and Internet of Things (ICIT), 2014 International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4799-7533-4
DOI :
10.1109/ICAIOT.2015.7111524
