Common interface for function optimization methods which depend on having both an objective function and a gradient function definition available. More...
#include <IGradientOptimizationMethod.h>


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... | |
Common interface for function optimization methods which depend on having both an objective function and a gradient function definition available.
HmetalT, 16.03.2017.
Definition at line 34 of file IGradientOptimizationMethod.h.
|
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.
|
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.
| parameter1 | The first parameter. |