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

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

An attempt of finding an appropriate number of convolutional layers in convolutional neural networks is made. The benchmark datasets are CIFAR-10, NORB and EEACL26, whose diversity and heterogeneousness must serve for a general applicability of a rule presumed to yield that number. The rule is drawn...

Full description

Bibliographic Details
Main Author: Romanuke Vadim V.
Format: Article
Language:English
Published: Sciendo 2018-07-01
Series:Electrical, Control and Communication Engineering
Subjects:
convolutional neural networks
convolutional layers
error rate
hyperparameters
performance
Online Access:https://doi.org/10.2478/ecce-2018-0006

Internet

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

Similar Items