MLask 1.0.0
A custom c++ deep learning library
Loading...
Searching...
No Matches
ActivationFunction.hpp
Go to the documentation of this file.
1#pragma once
2#include "Layer.hpp"
3
4namespace mlask{
8class ActivationFunction : public Layer{
9private:
10 vectorIn input_;
15 virtual float_t activate(float_t input) = 0;
20 virtual float_t derived(float_t input) = 0;
21public:
23 vectorOut forward(vectorIn)override;
27 void fit(float_t learning_rate)override{};
29 std::string str()const override{ return "Activation Function"; }
30};
31}
base class for Activation Functions, meant for simplicity in definition.
Definition ActivationFunction.hpp:8
vectorIn backward(vectorOut) override
Defines a way to backpropagate error in backropagation algorithm.
Definition ActivationFunction.cpp:10
vectorOut forward(vectorIn) override
Defines a way to move forward in a neural network.
Definition ActivationFunction.cpp:5
void fit(float_t learning_rate) override
Describes how the layer 'learns', meaning it defines how layer updates itself.
Definition ActivationFunction.hpp:27
std::string str() const override
Returns a string representation of the layer.
Definition ActivationFunction.hpp:29
Base class for all layers in the neural network.
Definition Layer.hpp:10
Definition LeakyRelu.hpp:4
Eigen::Matrix< float_t, Eigen::Dynamic, 1 > vectorOut
Definition types.hpp:17
float float_t
Definition types.hpp:12
Eigen::Matrix< float_t, Eigen::Dynamic, 1 > vectorIn
Definition types.hpp:16