A new node selection method of Deep Belief Network based on similarity

DOI

10.2991/amcce-17.2017.112How to use a DOI?

Keywords

deep belief network; node selection; similarity; deep learning; unsupervised learning

Abstract

Research on the node selection problem in Deep Belief Network(DBN). A new node selection model based on similarity is proposed to select nodes in the pre-training process of DBN, which is an unsupervised process. Firstly, extracting the nodes feature from pre-training weight matrix, and then comparing them each other to get the similarity matrix, and using the similarity matrix to select nodes and reusing the nodes. Finally,the test on MINIST data set proves that the new model has better performance.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Leifang Yan
AU  - MingYan Jiang
PY  - 2017/03
DA  - 2017/03
TI  - A new node selection method of Deep Belief Network based on similarity
BT  - Proceedings of the 2017 2nd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2017)
PB  - Atlantis Press
SP  - 645
EP  - 649
SN  - 2352-5401
UR  - https://doi.org/10.2991/amcce-17.2017.112
DO  - 10.2991/amcce-17.2017.112
ID  - Yan2017/03
ER  -