keras
Introduction
1. Examples
2. Optimizers
3. Objectives
4. Models
5. Activations
6. Initializations
7. Regularizers
8. Constraints
9. Callbacks
10. Datasets
11. Layers, Core Layers
12. Layers, Convolutional Layers
13. Layers, Recurrent Layers
14. Layers, Advanced Activations Layers
15. Layers, Normalization Layers
16. Layers, Embedding Layers
17. Layers, Containers
18. Preprocessing, Sequence Preprocessing
19. Preprocessing, Text Preprocessing
20. Preprocessing, Image Preprocessing
21. Utils, Visualization Utilities

keras

LeakyReLU

keras.layers.advanced_activations.LeakyReLU(alpha=0.3)

Special version of a Rectified Linear Unit that allows a small gradient when the unit is not active (f(x) = alpha*x for x < 0).

Input shape: This layer does not assume a specific input shape. As a result, it cannot be used as the first layer in a model.
Output shape: Same as input.
Arguments:
- alpha: float >= 0. Negative slope coefficient.

PReLU

keras.layers.advanced_activations.PReLU(input_shape)

Parametrized linear unit. Similar to a LeakyReLU, where each input unit has its alpha coefficient, and where these coefficients are learned during training.

Input shape: Same as input_shape. This layer cannot be used as first layer in a model.
Output shape: Same as input.
Arguments:
- input_shape: tuple.
References:
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification