Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Convolutional Deep Networks for Visual Data Classification

Convolutional Deep Networks for Visual Data Classification 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. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neural Processing Letters Springer Journals

Convolutional Deep Networks for Visual Data Classification

Download PDF
11 pages

Loading next page...
 
/lp/springer-journal/convolutional-deep-networks-for-visual-data-classification-bnUnzI2Tc1

References (12)

Publisher
Springer Journals
Copyright
Copyright © 2012 by Springer Science+Business Media New York
Subject
Computer Science; Artificial Intelligence (incl. Robotics); Statistical Physics, Dynamical Systems and Complexity; Computational Intelligence
ISSN
1370-4621
eISSN
1573-773X
DOI
10.1007/s11063-012-9260-y
Publisher site
See Article on Publisher Site

Abstract

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.

Journal

Neural Processing Letters – Springer Journals

Published: Nov 20, 2012

There are no references for this article.