base class for Activation Functions, meant for simplicity in definition. More...
#include <ActivationFunction.hpp>
Public Member Functions | |
| vectorOut | forward (vectorIn) override |
| Defines a way to move forward in a neural network. | |
| vectorIn | backward (vectorOut) override |
| Defines a way to backpropagate error in backropagation algorithm. | |
| void | fit (float_t learning_rate) override |
| Describes how the layer 'learns', meaning it defines how layer updates itself. | |
| std::string | str () const override |
| Returns a string representation of the layer. | |
 Public Member Functions inherited from mlask::Layer | |
| std::size_t | getIn () const |
| std::size_t | getOut () const |
| virtual | ~Layer ()=default |
| virtual bool | tryConvertToONNX (onnx::GraphProto *graph, std::string input, std::string output) const |
| Converts the layer to ONNX format. If the layer cannot be converted, it should return false. | |
Additional Inherited Members | |
| Protected Attributes inherited from mlask::Layer | |
| std::size_t | in_ |
| std::size_t | out_ |
Detailed Description
base class for Activation Functions, meant for simplicity in definition.
it strips children from fit method override must and also make it easy to define forrward and backward passes via activate and derived functions that act on a single value, rather than entire vector.
Member Function Documentation
◆ backward()
Defines a way to backpropagate error in backropagation algorithm.
Implements mlask::Layer.
◆ fit()
Describes how the layer 'learns', meaning it defines how layer updates itself.
Implements mlask::Layer.
◆ forward()
Defines a way to move forward in a neural network.
Implements mlask::Layer.
◆ str()
|
inlineoverridevirtual |
Returns a string representation of the layer.
Reimplemented from mlask::Layer.
Reimplemented in mlask::LeakyRelu, mlask::Relu, mlask::Sigmoid, and mlask::Tanh.
The documentation for this class was generated from the following files:
- include/ActivationFunction.hpp
- src/ActivationFunction.cpp
