Name
Title | ||
|---|---|---|
Enhancing Batch Normalized Convolutional Networks using Displaced Rectifier Linear Units: A Systematic Comparative Study |
Abstract | ||
|---|---|---|
•Enhanced nonlinearities may improve expert systems performance.•Proposal of the activation function DReLU.•DReLU presents the best training speed in all cases.•DReLU enhances the ReLU performance in all scenarios.•DReLU provides the best test accuracy in almost all experiments. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1016/j.eswa.2019.01.066 | Expert Systems with Applications |
Keywords | Field | DocType |
DReLU,Activation function,Batch normalization,Comparative study,Convolutional Neural Networks,Deep learning | Identity function,Residual,Rectifier,Normalization (statistics),Convolutional neural network,Activation function,Computer science,Artificial intelligence,Deep learning,Machine learning,Statistical hypothesis testing | Journal |
Volume | ISSN | Citations |
124 | 0957-4174 | 1 |
PageRank | References | Authors |
0.35 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| David Macêdo | 1 | 7 | 3.16 |
| Cleber Zanchettin | 2 | 127 | 21.14 |
| Adriano L. I. Oliveira | 3 | 364 | 36.36 |
| Teresa Bernarda Ludermir | 4 | 928 | 108.14 |