Information Theoretical Analysis of Deep Learning Representations

説明

Although deep learning shows high performance in pattern recognition and machine learning, the reasons are little clarified. To tackle this problem, we calculated the information theoretical variables of representations in hidden layers and analyzed their relationship to the performance. We found that the entropy and the mutual information decrease in a different way as the layer gets deeper. This suggests that the information theoretical variables may become a criterion to determine the number of layers in deep learning.

詳細情報 詳細情報について

問題の指摘

ページトップへ