Supposed Maximum Mutual Information for Improving Generalization and Interpretation of Multi-Layered Neural Networks

Publié en ligne: 31 déc. 2018

Pages: 123 - 147

Reçu: 06 févr. 2018

Accepté: 13 août 2018

DOI: https://doi.org/10.2478/jaiscr-2018-0029

Mots clés

mutual information, disentanglement, generalization, interpretation

© 2018 Ryotaro Kamimura, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.