Serf, or Log-Softplus ERror activation Function, is a type of activation function which is self-regularized and nonmonotonic in nature. It belongs to the Swish family of functions. Serf is defined as:
$$f\left(x\right) = x\text{erf}\left(\ln\left(1 + e^{x}\right)\right)$$
Source: SERF: Towards better training of deep neural networks using log-Softplus ERror activation FunctionPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Sleep Quality | 1 | 14.29% |
Sleep Staging | 1 | 14.29% |
Image Classification | 1 | 14.29% |
Machine Translation | 1 | 14.29% |
Object Detection | 1 | 14.29% |
Sentiment Analysis | 1 | 14.29% |
Translation | 1 | 14.29% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |