Bibliographic Details
| Title: |
Bidirectional clustering of weights for neural networks with common weights. |
| Authors: |
Saito, Kazumi1, Nakano, Ryohei2 |
| Source: |
Systems & Computers in Japan. 9/15/2007, Vol. 38 Issue 10, p46-57. 12p. 9 Charts, 2 Graphs. |
| Subjects: |
Artificial neural networks, Computer network design & construction, Computer research, Data mining, Cluster analysis (Statistics), Error functions, Polynomials |
| Abstract: |
This paper proposes a method which succinctly structures neural networks having a few thousand weights. Here structuring means weight sharing where weights in a network are divided into clusters and weights within a cluster have the same value. We newly introduce a weight sharing technique called bidirectional clustering of weights (BCW), together with second-order optimal criteria for both cluster merging and splitting. Our experiments using two artificial data sets showed that the BCW method works well to find a succinct network structure from a neural network having about 2000 weights in both regression and classification problems. © 2007 Wiley Periodicals, Inc. Syst Comp Jpn, 38(10): 46–57, 2007; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.20535 [ABSTRACT FROM AUTHOR] |
|
Copyright of Systems & Computers in Japan is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Engineering Source |
