Journals
Publish with us
Publishing partnerships
About us
Blog
Computational Intelligence and Neuroscience
Journal overview
For authors
For reviewers
For editors
Table of Contents
Special Issues
Computational Intelligence and Neuroscience
/
2021
/
Article
/
Tab 4
/
Research Article
AdaCN: An Adaptive Cubic Newton Method for Nonconvex Stochastic Optimization
Table 4
Test accuracy of VGG11, ResNet34, and DenseNet121 on CIFAR100.
Model
Adam
SGD
AdaBound
Apollo
AdaCN
VGG11
58.96
66.01
65.92
58.50
65.51
ResNet34
71.39
76.98
76.88
76.42
77.11
DenseNet121
71.85
79.35
79.00
79.01
79.50
The best results are shown in bold.