|
mlpack
master
|
Implementation of the Linear layer class. More...
Public Member Functions | |
| Linear () | |
| Create the Linear object. More... | |
| Linear (const size_t inSize, const size_t outSize) | |
| Create the Linear layer object using the specified number of units. More... | |
| template<typename eT > | |
| void | Backward (const arma::Mat< eT > &&, 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... | |
| OutputDataType const & | Delta () const |
| Get the delta. More... | |
| OutputDataType & | Delta () |
| Modify the delta. More... | |
| template<typename eT > | |
| 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<typename eT > | |
| void | Gradient (const arma::Mat< eT > &&input, 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... | |
| OutputDataType const & | OutputParameter () const |
| Get the output parameter. More... | |
| OutputDataType & | OutputParameter () |
| Modify the output parameter. More... | |
| OutputDataType const & | Parameters () const |
| Get the parameters. More... | |
| OutputDataType & | Parameters () |
| Modify the parameters. More... | |
| void | Reset () |
| template<typename Archive > | |
| void | Serialize (Archive &ar, const unsigned int) |
| Serialize the layer. More... | |
Private Attributes | |
| OutputDataType | bias |
| Locally-stored bias term parameters. More... | |
| OutputDataType | delta |
| Locally-stored delta object. More... | |
| OutputDataType | gradient |
| Locally-stored gradient object. More... | |
| InputDataType | inputParameter |
| Locally-stored input parameter object. More... | |
| size_t | inSize |
| Locally-stored number of input units. More... | |
| OutputDataType | outputParameter |
| Locally-stored output parameter object. More... | |
| size_t | outSize |
| Locally-stored number of output units. More... | |
| OutputDataType | weight |
| Locally-stored weight paramters. More... | |
| OutputDataType | weights |
| Locally-stored weight object. More... | |
Implementation of the Linear layer class.
The Linear class represents a single layer of a neural network.
| 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 49 of file layer_types.hpp.
| mlpack::ann::Linear< InputDataType, OutputDataType >::Linear | ( | ) |
Create the Linear object.
| mlpack::ann::Linear< InputDataType, OutputDataType >::Linear | ( | const size_t | inSize, |
| const size_t | outSize | ||
| ) |
Create the Linear layer object using the specified number of units.
| inSize | The number of input units. |
| outSize | The number of output units. |
| void mlpack::ann::Linear< InputDataType, OutputDataType >::Backward | ( | const arma::Mat< eT > && | , |
| 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.
| input | The propagated input activation. |
| gy | The backpropagated error. |
| g | The calculated gradient. |
|
inline |
Get the delta.
Definition at line 107 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::delta.
|
inline |
Modify the delta.
Definition at line 109 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::delta.
| void mlpack::ann::Linear< InputDataType, OutputDataType >::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.
| input | Input data used for evaluating the specified function. |
| output | Resulting output activation. |
| void mlpack::ann::Linear< InputDataType, OutputDataType >::Gradient | ( | const arma::Mat< eT > && | input, |
| arma::Mat< eT > && | error, | ||
| arma::Mat< eT > && | gradient | ||
| ) |
|
inline |
Get the gradient.
Definition at line 112 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::gradient.
|
inline |
Modify the gradient.
Definition at line 114 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::gradient, and mlpack::ann::Linear< InputDataType, OutputDataType >::Serialize().
|
inline |
Get the input parameter.
Definition at line 97 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::inputParameter.
|
inline |
Modify the input parameter.
Definition at line 99 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::inputParameter.
|
inline |
Get the output parameter.
Definition at line 102 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::outputParameter.
|
inline |
Modify the output parameter.
Definition at line 104 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::outputParameter.
|
inline |
Get the parameters.
Definition at line 92 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::weights.
|
inline |
Modify the parameters.
Definition at line 94 of file linear.hpp.
References mlpack::ann::Linear< InputDataType, OutputDataType >::weights.
| void mlpack::ann::Linear< InputDataType, OutputDataType >::Reset | ( | ) |
| void mlpack::ann::Linear< InputDataType, OutputDataType >::Serialize | ( | Archive & | ar, |
| const unsigned | int | ||
| ) |
Serialize the layer.
Referenced by mlpack::ann::Linear< InputDataType, OutputDataType >::Gradient().
|
private |
Locally-stored bias term parameters.
Definition at line 136 of file linear.hpp.
|
private |
Locally-stored delta object.
Definition at line 139 of file linear.hpp.
Referenced by mlpack::ann::Linear< InputDataType, OutputDataType >::Delta().
|
private |
Locally-stored gradient object.
Definition at line 142 of file linear.hpp.
Referenced by mlpack::ann::Linear< InputDataType, OutputDataType >::Gradient().
|
private |
Locally-stored input parameter object.
Definition at line 145 of file linear.hpp.
Referenced by mlpack::ann::Linear< InputDataType, OutputDataType >::InputParameter().
|
private |
Locally-stored number of input units.
Definition at line 124 of file linear.hpp.
|
private |
Locally-stored output parameter object.
Definition at line 148 of file linear.hpp.
Referenced by mlpack::ann::Linear< InputDataType, OutputDataType >::OutputParameter().
|
private |
Locally-stored number of output units.
Definition at line 127 of file linear.hpp.
|
private |
Locally-stored weight paramters.
Definition at line 133 of file linear.hpp.
|
private |
Locally-stored weight object.
Definition at line 130 of file linear.hpp.
Referenced by mlpack::ann::Linear< InputDataType, OutputDataType >::Parameters().
1.8.11