論文

査読有り
2018年1月

Data Visualization for Deep Neural Networks Based on Interlayer Canonical Correlation Analysis

Transactions of ISCIE
  • Akinori Hidaka and Takio Kurita

31
1
開始ページ
10
終了ページ
20
記述言語
英語
掲載種別
研究論文(学術雑誌)
出版者・発行元
The Institute of Systems, Control and Information Engineers (ISCIE)

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.

エクスポート
BibTeX RIS