#include <inspectable.h>
Inherited by AbstractController, and AbstractWiring.
Inheritance diagram for Inspectable:
Public Types | |
typedef std::string | iparamkey |
typedef double | iparamval |
typedef std::list< iparamkey > | iparamkeylist |
typedef std::list< iparamval > | iparamvallist |
typedef Inspectable::ILayer | ILayer |
typedef Inspectable::IConnection | IConnection |
typedef std::list< ILayer > | ilayerlist |
typedef std::list< IConnection > | iconnectionlist |
Public Member Functions | |
virtual | ~Inspectable () |
virtual iparamkeylist | getInternalParamNames () const =0 |
The list of the names of all internal parameters given by getInternalParams(). | |
virtual iparamvallist | getInternalParams () const =0 |
virtual ilayerlist | getStructuralLayers () const |
Specifies which parameter vector forms a structural layer (in terms of a neural network) The ordering is important. | |
virtual iconnectionlist | getStructuralConnections () const |
Specifies which parameter matrix forms a connection between layers (in terms of a neural network) The orderning is not important. |
That means that one can read out some internal parameters indentified by string keys
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
The list of the names of all internal parameters given by getInternalParams(). The naming convention is "v[i]" for vectors and "A[i][j]" for matrices, where i, j start at 0.
Implemented in DerController, FFNNController, InvertMotorBigModel, InvertMotorNStep, InvertMotorSpace, InvertNChannelController, ProActive, ProActive2, SineController, AbstractWiring, One2OneWiring, DemoController, MultiController, and SimpleController.
|
|
Implemented in DerController, FFNNController, InvertMotorBigModel, InvertMotorNStep, InvertMotorSpace, InvertNChannelController, ProActive, ProActive2, SineController, AbstractWiring, One2OneWiring, DemoController, MultiController, and SimpleController.
|
|
Specifies which parameter matrix forms a connection between layers (in terms of a neural network) The orderning is not important.
Reimplemented in DerController, InvertMotorBigModel, InvertMotorNStep, InvertMotorSpace, and InvertNChannelController.
|
|
Specifies which parameter vector forms a structural layer (in terms of a neural network) The ordering is important. The first entry is the input layer and so on.
Reimplemented in DerController, InvertMotorBigModel, InvertMotorNStep, InvertMotorSpace, and InvertNChannelController.
|