ModelWithMemoryAdapter Class Reference
multi layer neural network with configurable activation functions More...
#include <modelwithmemoryadapter.h>
Inherits InvertableModel.
Classes | |
| struct | Pat |
Public Member Functions | |
| ModelWithMemoryAdapter (InvertableModel *model, int memorySize, int numPatternsPerStep) | |
| virtual | ~ModelWithMemoryAdapter () |
| virtual void | init (unsigned int inputDim, unsigned int outputDim, double unit_map=0.0, RandGen *randGen=0) |
| initialisation of the network with the given number of input and output units | |
| virtual const matrix::Matrix | learn (const matrix::Matrix &input, const matrix::Matrix &nom_output, double learnRateFactor=1) |
| learn the input output mapping but also learn mappings from the memory. | |
| virtual const matrix::Matrix | process (const matrix::Matrix &input) |
| passive processing of the input (this function is not constant since a recurrent network for example might change internal states | |
| virtual const matrix::Matrix | response (const matrix::Matrix &input) const |
| calculates the partial derivative of the of the output with repect to the input (Jacobi matrix). | |
| virtual const matrix::Matrix | inversion (const matrix::Matrix &input, const matrix::Matrix &xsi) const |
| calculates the input shift v to given output shift xsi via pseudo inversion. | |
| virtual unsigned int | getInputDim () const |
| returns the number of input neurons | |
| virtual unsigned int | getOutputDim () const |
| returns the number of output neurons | |
| virtual void | damp (double damping) |
| damps the weights and the biases by multiplying (1-damping) | |
| Inspectable * | getModel () |
| const Inspectable * | getModel () const |
| bool | store (FILE *f) const |
| stores the layer binary into file stream | |
| bool | restore (FILE *f) |
| restores the layer binary from file stream | |
| virtual iparamkeylist | getInternalParamNames () const |
| The list of the names of all internal parameters given by getInternalParams(). | |
| virtual iparamvallist | getInternalParams () const |
| 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. | |
Protected Attributes | |
| InvertableModel * | model |
| int | memorySize |
| int | numPatternsPerStep |
| std::vector< Pat > | memory |
| vector of input output mappings | |
| RandGen * | randGen |
Detailed Description
multi layer neural network with configurable activation functions
Constructor & Destructor Documentation
| ModelWithMemoryAdapter | ( | InvertableModel * | model, | |
| int | memorySize, | |||
| int | numPatternsPerStep | |||
| ) |
- Parameters:
-
model pointer to model to accomplish by memory memorySize number of pattern that are stored numPatternsPerStep number of past patterns to learn each step
| virtual ~ModelWithMemoryAdapter | ( | ) | [inline, virtual] |
Member Function Documentation
| virtual void damp | ( | double | damping | ) | [inline, virtual] |
damps the weights and the biases by multiplying (1-damping)
Implements AbstractModel.
| virtual unsigned int getInputDim | ( | ) | const [inline, virtual] |
returns the number of input neurons
Implements AbstractModel.
| virtual iparamkeylist getInternalParamNames | ( | ) | const [inline, virtual] |
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.
- Returns:
- : list of keys
Reimplemented from Inspectable.
| virtual iparamvallist getInternalParams | ( | ) | const [inline, virtual] |
- Returns:
- : list of values
Reimplemented from Inspectable.
| const Inspectable* getModel | ( | ) | const [inline] |
| Inspectable* getModel | ( | ) | [inline] |
| virtual unsigned int getOutputDim | ( | ) | const [inline, virtual] |
returns the number of output neurons
Implements AbstractModel.
| virtual iconnectionlist getStructuralConnections | ( | ) | const [inline, virtual] |
Specifies which parameter matrix forms a connection between layers (in terms of a neural network) The orderning is not important.
- Returns:
- : list of layer names with dimension
Reimplemented from Inspectable.
| virtual ilayerlist getStructuralLayers | ( | ) | const [inline, virtual] |
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.
- Returns:
- : list of layer names with dimension
Reimplemented from Inspectable.
| void init | ( | unsigned int | inputDim, | |
| unsigned int | outputDim, | |||
| double | unit_map = 0.0, |
|||
| RandGen * | randGen = 0 | |||
| ) | [virtual] |
initialisation of the network with the given number of input and output units
- Parameters:
-
inputDim length of input vector outputDim length of output vector unit_map if 0 the parametes are choosen randomly. Otherwise the model is initialised to represent a unit_map with the given response strength. randGen pointer to random generator, if 0 an new one is used
Implements AbstractModel.
| virtual const matrix::Matrix inversion | ( | const matrix::Matrix & | input, | |
| const matrix::Matrix & | xsi | |||
| ) | const [inline, virtual] |
calculates the input shift v to given output shift xsi via pseudo inversion.
![\[o+\xi = \pi(i+v)\]](form_9.png)
The result is a vector of dimension inputdim
Implements InvertableModel.
| const Matrix learn | ( | const matrix::Matrix & | input, | |
| const matrix::Matrix & | nom_output, | |||
| double | learnRateFactor = 1 | |||
| ) | [virtual] |
learn the input output mapping but also learn mappings from the memory.
- See also:
- InvertableModel::learn
Implements AbstractModel.
| virtual const matrix::Matrix process | ( | const matrix::Matrix & | input | ) | [inline, virtual] |
passive processing of the input (this function is not constant since a recurrent network for example might change internal states
Implements AbstractModel.
| virtual const matrix::Matrix response | ( | const matrix::Matrix & | input | ) | const [inline, virtual] |
calculates the partial derivative of the of the output with repect to the input (Jacobi matrix).
![\[J_{ij} = \frac{\partial output_i}{\partial input_j}\]](form_8.png)
The result is a matrix of dimension (outputdim x inputdim)
Implements InvertableModel.
| bool restore | ( | FILE * | f | ) | [inline, virtual] |
restores the layer binary from file stream
Implements Storeable.
| bool store | ( | FILE * | f | ) | const [inline, virtual] |
stores the layer binary into file stream
Implements Storeable.
Member Data Documentation
int memorySize [protected] |
InvertableModel* model [protected] |
int numPatternsPerStep [protected] |
The documentation for this class was generated from the following files:
