Research Article
[Retracted] Improving Convolutional Neural Networks with Competitive Activation Function
Table 2
Classification results (%) with LeNet-5 on Fashion-MNIST.
| Method | Accuracy rate (%) |
| ReLU | 90.34 | LReLU | 90.37 | PReLU | 90.43 | ELU | 90.80 | SELU | 90.84 | Softplus | 88.87 | Swish | 89.93 | Mish | 90.25 | FReLU | 90.98 | PFREU-A | 91.09 | PFREU-B | 91.04 | PFREU-C | 91.21 |
|
|