2016年11月
Consecutive Dimensionality Reduction by Canonical Correlation Analysis for Visualization of Convolutional Neural Networks
Proc. of The 48th ISCIE International Symposium on Stochastic Systems Theory and Its Application
- 巻
- 2017
- 号
- 開始ページ
- 160
- 終了ページ
- 167
- 記述言語
- 英語
- 掲載種別
- 研究論文(国際会議プロシーディングス)
- DOI
- 10.5687/sss.2017.160
- 出版者・発行元
- The Institute of Systems, Control and Information Engineers
<p>In this paper, we develop a visualization tool suitable for deep neural networks (DNN). Although typical dimensionality reduction methods, such as principal component analysis (PCA), are useful to visualize highdimensional data as 2 or 3 dimensional representations, most of those methods focus their attention on how to create essential subspaces based only on a given unique feature representation. On the other hand, DNN naturally have consecutive multiple feature representations corresponding to their intermediate layers. In order to understand relationships of those consecutive intermediate layers, we utilize canonical correlation analysis (CCA) to visualize them in a unified subspace. Our method (called consecutive CCA) can visualize "feature flow" which represents movement of samples between two consecutive layers of DNN. By using standard benchmark datasets, we show that our visualization results contain much information that typical visualization methods (such as PCA) do not represent.</p>
- リンク情報
- ID情報
-
- DOI : 10.5687/sss.2017.160
- CiNii Articles ID : 130006192997