Activation Functions
Hard Sigmoid
Introduced by Courbariaux et al. in BinaryConnect: Training Deep Neural Networks with binary weights during propagationsThe Hard Sigmoid is an activation function used for neural networks of the form:
$$f\left(x\right) = \max\left(0, \min\left(1,\frac{\left(x+1\right)}{2}\right)\right)$$
Image Source: Rinat Maksutov
Source: BinaryConnect: Training Deep Neural Networks with binary weights during propagations
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Segmentation | 1 | 33.33% |
| Semantic Segmentation | 1 | 33.33% |
| Network Pruning | 1 | 33.33% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
