システム制御情報学会論文誌
Online ISSN : 2185-811X
Print ISSN : 1342-5668
ISSN-L : 1342-5668
論文
Data Visualization for Deep Neural Networks Based on Interlayer Canonical Correlation Analysis
Akinori HidakaTakio Kurita
著者情報
ジャーナル フリー

2018 年 31 巻 1 号 p. 10-20

詳細
抄録

In this paper, we develop data visualization methods which consider interlayer correlations in deep neural networks (DNN). In general, DNN naturally acquires multiple feature representations corresponding to their intermediate layers through their learning process. In order to understand relationships of those intermediate features which are strongly correlated with each other, we utilize canonical correlation analysis (CCA) to visualize the data distributions of different feature layers in a common subspace. Our method can grasp movement of samples between consecutive layers in DNN. By using standard benchmark data sets, we show that our visualization results contain much information that typical visualization methods (such as principal component analysis) usually do not represent.

著者関連情報
© 2018 The Institute of Systems, Control and Information Engineers
前の記事 次の記事
feedback
Top