Data Visualization for Deep Neural Networks Based on Interlayer Canonical Correlation Analysis
-
- Hidaka Akinori
- School of Science and Engineering, Tokyo Denki University
-
- Kurita Takio
- Department of Information Engineering, Hiroshima University
この論文をさがす
説明
<p>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.</p>
収録刊行物
-
- システム制御情報学会論文誌
-
システム制御情報学会論文誌 31 (1), 10-20, 2018
一般社団法人 システム制御情報学会
- Tweet
キーワード
詳細情報 詳細情報について
-
- CRID
- 1390001205167642496
-
- NII論文ID
- 130006707945
-
- NII書誌ID
- AN1013280X
-
- ISSN
- 2185811X
- 13425668
-
- NDL書誌ID
- 028755912
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- 抄録ライセンスフラグ
- 使用不可