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

Publicado en línea: 31 dic 2018

Páginas: 123 - 147

Recibido: 06 feb 2018

Aceptado: 13 ago 2018

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

Palabras clave

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.