An attempt of finding an appropriate number of convolutional layers in cnns based on benchmarks of heterogeneous datasets

Pubblicato online: 28 lug 2018

Pagine: 51 - 57

DOI: https://doi.org/10.2478/ecce-2018-0006

Parole chiave

convolutional neural networks, convolutional layers, error rate, hyperparameters, performance

© 2018 Vadim V. Romanuke, published by Sciendo

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