mlpack
master
|
Implementation of the reinforce normal layer. More...
Public Member Functions | |
ReinforceNormal (const double stdev) | |
Create the ReinforceNormal object. More... | |
template<typename DataType > | |
void | Backward (const DataType &&input, DataType &&, DataType &&g) |
Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. More... | |
OutputDataType & | Delta () const |
Get the delta. More... | |
OutputDataType & | Delta () |
Modify the delta. More... | |
bool | Deterministic () const |
Get the value of the deterministic parameter. More... | |
bool & | Deterministic () |
Modify the value of the deterministic parameter. 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... | |
InputDataType & | InputParameter () const |
Get the input parameter. More... | |
InputDataType & | InputParameter () |
Modify the input parameter. More... | |
OutputDataType & | OutputParameter () const |
Get the output parameter. More... | |
OutputDataType & | OutputParameter () |
Modify the output parameter. More... | |
double | Reward () const |
Get the value of the reward parameter. More... | |
double & | Reward () |
Modify the value of the deterministic parameter. More... | |
template<typename Archive > | |
void | Serialize (Archive &, const unsigned int) |
Serialize the layer. More... | |
Private Attributes | |
OutputDataType | delta |
Locally-stored delta object. More... | |
bool | deterministic |
If true use maximum a posteriori during the forward pass. More... | |
InputDataType | inputParameter |
Locally-stored input parameter object. More... | |
std::vector< arma::mat > | moduleInputParameter |
Locally-stored output module parameter parameters. More... | |
OutputDataType | outputParameter |
Locally-stored output parameter object. More... | |
double | reward |
Locally-stored reward parameter. More... | |
const double | stdev |
Standard deviation used during the forward and backward pass. More... | |
Implementation of the reinforce normal layer.
The reinforce normal layer implements the REINFORCE algorithm for the normal distribution.
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 29 of file reinforce_normal.hpp.
mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::ReinforceNormal | ( | const double | stdev | ) |
Create the ReinforceNormal object.
stdev | Standard deviation used during the forward and backward pass. |
void mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::Backward | ( | const DataType && | input, |
DataType && | , | ||
DataType && | g | ||
) |
Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through 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 72 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::delta.
|
inline |
Modify the delta.
Definition at line 74 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::delta.
|
inline |
Get the value of the deterministic parameter.
Definition at line 77 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::deterministic.
|
inline |
Modify the value of the deterministic parameter.
Definition at line 79 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::deterministic.
void mlpack::ann::ReinforceNormal< 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. |
|
inline |
Get the input parameter.
Definition at line 62 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::inputParameter.
|
inline |
Modify the input parameter.
Definition at line 64 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::inputParameter.
|
inline |
Get the output parameter.
Definition at line 67 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::outputParameter.
|
inline |
Modify the output parameter.
Definition at line 69 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::outputParameter.
|
inline |
Get the value of the reward parameter.
Definition at line 82 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::reward.
|
inline |
Modify the value of the deterministic parameter.
Definition at line 84 of file reinforce_normal.hpp.
References mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::reward, and mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::Serialize().
void mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::Serialize | ( | Archive & | , |
const unsigned | int | ||
) |
Serialize the layer.
Referenced by mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::Reward().
|
private |
Locally-stored delta object.
Definition at line 100 of file reinforce_normal.hpp.
Referenced by mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::Delta().
|
private |
If true use maximum a posteriori during the forward pass.
Definition at line 112 of file reinforce_normal.hpp.
Referenced by mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::Deterministic().
|
private |
Locally-stored input parameter object.
Definition at line 103 of file reinforce_normal.hpp.
Referenced by mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::InputParameter().
|
private |
Locally-stored output module parameter parameters.
Definition at line 109 of file reinforce_normal.hpp.
|
private |
Locally-stored output parameter object.
Definition at line 106 of file reinforce_normal.hpp.
Referenced by mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::OutputParameter().
|
private |
Locally-stored reward parameter.
Definition at line 97 of file reinforce_normal.hpp.
Referenced by mlpack::ann::ReinforceNormal< InputDataType, OutputDataType >::Reward().
|
private |
Standard deviation used during the forward and backward pass.
Definition at line 94 of file reinforce_normal.hpp.