NNFS
Neural network library from scratch
|
Base class for all activation functions. More...
#include <Activation.hpp>
Public Member Functions | |
Activation (ActivationType activation_type) | |
Construct a new Activation object. | |
Public Member Functions inherited from NNFS::Layer | |
Layer (LayerType type) | |
Construct a new Layer object. | |
virtual | ~Layer ()=default |
Basic destructor. | |
virtual void | forward (Eigen::MatrixXd &out, const Eigen::MatrixXd &x)=0 |
Forward pass of the layer. | |
virtual void | backward (Eigen::MatrixXd &out, const Eigen::MatrixXd &dx)=0 |
Backward pass of the layer. | |
Public Attributes | |
ActivationType | activation_type |
Public Attributes inherited from NNFS::Layer | |
LayerType | type |
Protected Attributes | |
Eigen::MatrixXd | _forward_input |
Base class for all activation functions.
This class is the base class for all activation functions. It provides the interface for all activation functions.
|
inline |
Construct a new Activation object.
activation_type | Type of activation function |
|
protected |
ActivationType NNFS::Activation::activation_type |