Back to articles
Volume: 28 | Article ID: art00013
Hierarchical Decomposition of Large Deep Networks
  DOI :  10.2352/ISSN.2470-1173.2016.19.COIMG-152  Published OnlineFebruary 2016

Deep networks have revolutionized the image, speech, and pattern recognition communities. Despite recent evidence showing deep networks can rival the human brain for visual object recognition, the expansion of such architectures to generalpurpose intelligent reasoning is intractable due to the number of training parameters. Hierarchical representations have been introduced, but either have been applied to small problems, or have been ad hoc in nature. This paper introduces a framework that automatically analyzes and configures a family of smaller deep networks as a replacement to a singular, larger network. By analyzing the linkage coefficients from confusion matrices and class boundaries from spectral clustering, class clusters and subclusters are automatically detected, enabling the framework to divide and conquer large classification problems. The resulting smaller networks are not only highly scalable, parallel and more practical to train, but also achieve higher classification accuracy. Numerous experiments on network classes, layers, and architecture configurations validate our results.

Subject Areas :
Views 12
Downloads 0
 articleview.views 12
 articleview.downloads 0
  Cite this article 

Sumanth Chennupati, Shagan Sah, Sai Nooka, Raymond Ptucha, "Hierarchical Decomposition of Large Deep Networksin Proc. IS&T Int’l. Symp. on Electronic Imaging: Computational Imaging XIV,  2016,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2016
Electronic Imaging
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA