NeuralEngine
A Game Engine with embeded Machine Learning algorithms based on Gaussian Processes.
NeuralEngine::MachineLearning::IGradientOptimizationMethod< Scalar > Class Template Referenceabstract

Common interface for function optimization methods which depend on having both an objective function and a gradient function definition available. More...

#include <IGradientOptimizationMethod.h>

Inheritance diagram for NeuralEngine::MachineLearning::IGradientOptimizationMethod< Scalar >:
Collaboration diagram for NeuralEngine::MachineLearning::IGradientOptimizationMethod< Scalar >:

Public Member Functions

virtual af::array GetGradient ()=0
 Gets a function returning the gradient vector of the function to be optimized for a given value of its free parameters. More...
 
virtual void SetGradient (af::array g)=0
 Sets a function returning the gradient vector of the function to be optimized for a given value of its free parameters. More...
 
- Public Member Functions inherited from NeuralEngine::MachineLearning::IOptimizationMethod< Scalar >
virtual int GetNumberOfVariables ()=0
 Gets the number of variables (free parameters) in the optimization problem. More...
 
virtual af::array GetSolution ()=0
 Gets the current solution found, the values of the parameters which optimizes the function. More...
 
virtual void SetSolution (af::array &x)=0
 Gets a solution. More...
 
virtual Scalar GetValue ()=0
 Gets the output of the function at the current Solution. More...
 
virtual bool Minimize (int *cycle=nullptr)=0
 Finds the minimum value of a function. The solution vector will be made available at the Solution property. More...
 
virtual bool Maximize (int *cycle=nullptr)=0
 Finds the maximum value of a function. The solution vector will be made available at the Solution property. More...
 

Detailed Description

template<typename Scalar>
class NeuralEngine::MachineLearning::IGradientOptimizationMethod< Scalar >

Common interface for function optimization methods which depend on having both an objective function and a gradient function definition available.

HmetalT, 16.03.2017.

See also
BroydenFletcherGoldfarbShanno, ConjugateGradient, ResilientBackpropagation

Definition at line 34 of file IGradientOptimizationMethod.h.

Member Function Documentation

◆ GetGradient()

template<typename Scalar >
virtual af::array NeuralEngine::MachineLearning::IGradientOptimizationMethod< Scalar >::GetGradient ( )
pure virtual

Gets a function returning the gradient vector of the function to be optimized for a given value of its free parameters.

HmetalT, 16.03.2017.

Returns
The gradient function.

◆ SetGradient()

template<typename Scalar >
virtual void NeuralEngine::MachineLearning::IGradientOptimizationMethod< Scalar >::SetGradient ( af::array  g)
pure virtual

Sets a function returning the gradient vector of the function to be optimized for a given value of its free parameters.

HmetalT, 16.03.2017.

Parameters
parameter1The first parameter.

The documentation for this class was generated from the following file: