Home > Papers

 
 
Pre-training convolutional neural networks
HUANG Yue * #
School of Information Science and Engineering, Xiamen University
*Correspondence author
#Submitted by
Subject:
Funding: Specialized Research Fund for the Doctoral Program of Higher Education（No.20120121120043）
Opened online:19 March 2015
Accepted by: none
Citation: HUANG Yue.Pre-training convolutional neural networks[OL]. [19 March 2015] http://en.paper.edu.cn/en_releasepaper/content/4634372
 
 
Convolutional neural networks (ConvNets) is multi-stages trainable architecture that can learn invariant features in recognition. Applications of ConvNets in 'Big Data' are always limited to some challenges: 1) the labeled data is scarce and the labeled data is abundant; 2) tedious training procedure is required frequently with updated training samples. In this work, an efficient principle component analysis(PCA) based pre-training strategy has been introduced to reduce the high computational cost of kernel training in ConvNets, and to make the system be more robust to insufficient labeled training data. Two datasets MNIST and VLOGO are employed to validate the proposed work. The classification experiments results have demonstrated that the proposed pre-training ConvNets is able to accelerate the training procedure and reduce the requirement of sufficient labeled training samples.
Keywords:signal and information processing; convolutional neural networks; pre-training; recognition; MNIST; vehicle logo
 
 
 

For this paper
  • ● PDF (0B)
  • ● Revision 0 　　
  • ● Print this paper
  • ● Recommend this paper to a friend
  • ● Add to my favorite list

    Saved Papers

    Please enter a name for this paper to be shown in your personalized Saved Papers list

Tags
Add yours

Related Papers

Statistics
PDF Downloaded 239
Bookmarked 0
Recommend 5
Comments Array
Submit your papers