Characterization of Symbolic Rules Embedded in Deep DIMLP Networks: A Challenge to Transparency of Deep Learning

Publicado en línea: 03 may 2017

Páginas: 265 - 286

Recibido: 14 feb 2017

Aceptado: 20 mar 2017

DOI: https://doi.org/10.1515/jaiscr-2017-0019

Palabras clave

ensembles, Deep Learning, rule extraction, feature detectors

© 2017

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