Implementation of the NoisyLinear layer class. More...
Public Member Functions | |
| NoisyLinear () | |
| Create the NoisyLinear object. More... | |
| NoisyLinear (const size_t inSize, const size_t outSize) | |
| Create the NoisyLinear layer object using the specified number of units. More... | |
| NoisyLinear (const NoisyLinear &) | |
| Copy constructor. More... | |
| template | |
| void | Backward (const arma::Mat< eT > &, const arma::Mat< eT > &gy, arma::Mat< eT > &g) |
| Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f. More... | |
| arma::mat & | Bias () |
| Modify the bias weights of the layer. More... | |
| OutputDataType const & | Delta () const |
| Get the delta. More... | |
| OutputDataType & | Delta () |
| Modify the delta. More... | |
| template | |
| void | Forward (const arma::Mat< eT > &input, arma::Mat< eT > &output) |
| Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More... | |
| template | |
| void | Gradient (const arma::Mat< eT > &input, const arma::Mat< eT > &error, arma::Mat< eT > &gradient) |
| OutputDataType const & | Gradient () const |
| Get the gradient. More... | |
| OutputDataType & | Gradient () |
| Modify the gradient. More... | |
| InputDataType const & | InputParameter () const |
| Get the input parameter. More... | |
| InputDataType & | InputParameter () |
| Modify the input parameter. More... | |
| size_t | InputSize () const |
| Get the input size. More... | |
| OutputDataType const & | OutputParameter () const |
| Get the output parameter. More... | |
| OutputDataType & | OutputParameter () |
| Modify the output parameter. More... | |
| size_t | OutputSize () const |
| Get the output size. More... | |
| OutputDataType const & | Parameters () const |
| Get the parameters. More... | |
| OutputDataType & | Parameters () |
| Modify the parameters. More... | |
| void | Reset () |
| void | ResetNoise () |
| void | ResetParameters () |
| template | |
| void | serialize (Archive &ar, const unsigned int) |
| Serialize the layer. More... | |
Detailed Description
template
class mlpack::ann::NoisyLinear< InputDataType, OutputDataType >
Implementation of the NoisyLinear layer class.
It represents a single layer of a neural network, with parametric noise added to its weights.
- Template Parameters
-
InputDataType Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube). OutputDataType Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
Definition at line 100 of file layer_types.hpp.
Constructor & Destructor Documentation
◆ NoisyLinear() [1/3]
| NoisyLinear | ( | ) |
Create the NoisyLinear object.
◆ NoisyLinear() [2/3]
| NoisyLinear | ( | const size_t | inSize, |
| const size_t | outSize | ||
| ) |
Create the NoisyLinear layer object using the specified number of units.
- Parameters
-
inSize The number of input units. outSize The number of output units.
◆ NoisyLinear() [3/3]
| NoisyLinear | ( | const NoisyLinear< InputDataType, OutputDataType > & | ) |
Copy constructor.
Member Function Documentation
◆ Backward()
| void Backward | ( | const arma::Mat< eT > & | , |
| const arma::Mat< eT > & | gy, | ||
| arma::Mat< eT > & | g | ||
| ) |
Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f.
Using the results from the feed forward pass.
- Parameters
-
* (input) The propagated input activation. gy The backpropagated error. g The calculated gradient.
◆ Bias()
|
inline |
Modify the bias weights of the layer.
Definition at line 134 of file noisylinear.hpp.
References NoisyLinear< InputDataType, OutputDataType >::serialize().
◆ Delta() [1/2]
|
inline |
Get the delta.
Definition at line 118 of file noisylinear.hpp.
◆ Delta() [2/2]
|
inline |
Modify the delta.
Definition at line 120 of file noisylinear.hpp.
◆ Forward()
| void Forward | ( | const arma::Mat< eT > & | input, |
| arma::Mat< eT > & | output | ||
| ) |
Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f.
- Parameters
-
input Input data used for evaluating the specified function. output Resulting output activation.
◆ Gradient() [1/3]
| void Gradient | ( | const arma::Mat< eT > & | input, |
| const arma::Mat< eT > & | error, | ||
| arma::Mat< eT > & | gradient | ||
| ) |
◆ Gradient() [2/3]
|
inline |
Get the gradient.
Definition at line 129 of file noisylinear.hpp.
◆ Gradient() [3/3]
|
inline |
Modify the gradient.
Definition at line 131 of file noisylinear.hpp.
◆ InputParameter() [1/2]
|
inline |
Get the input parameter.
Definition at line 108 of file noisylinear.hpp.
◆ InputParameter() [2/2]
|
inline |
Modify the input parameter.
Definition at line 110 of file noisylinear.hpp.
◆ InputSize()
|
inline |
Get the input size.
Definition at line 123 of file noisylinear.hpp.
◆ OutputParameter() [1/2]
|
inline |
Get the output parameter.
Definition at line 113 of file noisylinear.hpp.
◆ OutputParameter() [2/2]
|
inline |
Modify the output parameter.
Definition at line 115 of file noisylinear.hpp.
◆ OutputSize()
|
inline |
Get the output size.
Definition at line 126 of file noisylinear.hpp.
◆ Parameters() [1/2]
|
inline |
Get the parameters.
Definition at line 103 of file noisylinear.hpp.
◆ Parameters() [2/2]
|
inline |
Modify the parameters.
Definition at line 105 of file noisylinear.hpp.
◆ Reset()
| void Reset | ( | ) |
◆ ResetNoise()
| void ResetNoise | ( | ) |
◆ ResetParameters()
| void ResetParameters | ( | ) |
◆ serialize()
| void serialize | ( | Archive & | ar, |
| const unsigned | int | ||
| ) |
Serialize the layer.
Referenced by NoisyLinear< InputDataType, OutputDataType >::Bias().
The documentation for this class was generated from the following files:
- /home/jenkins-mlpack/mlpack.org/_src/mlpack-3.4.2/src/mlpack/methods/ann/layer/layer_types.hpp
- /home/jenkins-mlpack/mlpack.org/_src/mlpack-3.4.2/src/mlpack/methods/ann/layer/noisylinear.hpp