Neural Processing Letters

, Volume 38, Issue 1, pp 17–27

Convolutional Deep Networks for Visual Data Classification


DOI: 10.1007/s11063-012-9260-y

Cite this article as:
Zhou, S., Chen, Q. & Wang, X. Neural Process Lett (2013) 38: 17. doi:10.1007/s11063-012-9260-y


This paper develops a semi-supervised learning algorithm called convolutional deep networks (CDN), to address the image classification problem with deep learning. First, we construct the previous several hidden layers using convolutional restricted Boltzmann machines, which can reduce the dimension and abstract the information of the images effectively. Second, we construct the following hidden layers using restricted Boltzmann machines, which can abstract the information of images quickly. Third, the constructed deep architecture is fine-tuned by gradient-descent based supervised learning with an exponential loss function. CDN can reduce the dimension and abstract the information of the images at the same time efficiently. More importantly, the abstraction and classification procedure of CDN use the same deep architecture to optimize the same parameter in different steps continuously, which can improve the learning ability effectively. We did several experiments on two standard image datasets, and show that CDN are competitive with both representative semi-supervised classifiers and existing deep learning techniques.


Semi-supervised learning Deep learning Convolutional neural networks Visual data classification 

Copyright information

© Springer Science+Business Media New York 2012

Authors and Affiliations

  1. 1.Key Laboratory of Network Oriented Intelligent Computation, Shenzhen Graduate SchoolHarbin Institute of TechnologyHarbinPeople’s Republic of China

Personalised recommendations