Smooth Non-increasing Square Spatial Extents of Filters in Convolutional Layers of CNNs for Image Classification Problems

Smooth Non-increasing Square Spatial Extents of Filters in Convolutional Layers of CNNs for Image Classification Problems

The present paper considers an open problem of setting hyperparameters for convolutional neural networks aimed at image classification. Since selecting filter spatial extents for convolutional layers is a topical problem, it is approximately solved by accumulating statistics of the neural network pe...

Full description

Bibliographic Details
Main Author: Romanuke Vadim V.
Format: Article
Language:English
Published: Sciendo 2018-05-01
Series:Applied Computer Systems
Subjects:
convolutional layer
convolutional neural networks
filters
hyperparameters
network architecture
square spatial extents of filters
Online Access:https://doi.org/10.2478/acss-2018-0007

Internet

https://doi.org/10.2478/acss-2018-0007

Similar Items