\section{Poisson\+N\+L\+L\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1PoissonNLLLoss}\index{Poisson\+N\+L\+L\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$@{Poisson\+N\+L\+L\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$}} Implementation of the Poisson negative log likelihood loss. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Poisson\+N\+L\+L\+Loss} (const bool log\+Input=true, const bool full=false, const typename Input\+Data\+Type\+::elem\+\_\+type eps=1e-\/08, const bool mean=true) \begin{DoxyCompactList}\small\item\em Create the \doxyref{Poisson\+N\+L\+L\+Loss}{p.}{classmlpack_1_1ann_1_1PoissonNLLLoss} object. \end{DoxyCompactList}\item {\footnotesize template$<$typename Input\+Type , typename Target\+Type , typename Output\+Type $>$ }\\void \textbf{ Backward} (const Input\+Type \&input, const Target\+Type \&target, Output\+Type \&output) \begin{DoxyCompactList}\small\item\em Ordinary feed backward pass of a neural network. \end{DoxyCompactList}\item Input\+Data\+Type\+::elem\+\_\+type \textbf{ Eps} () const \begin{DoxyCompactList}\small\item\em Get the value of eps. \end{DoxyCompactList}\item Input\+Data\+Type\+::elem\+\_\+type \& \textbf{ Eps} () \begin{DoxyCompactList}\small\item\em Modify the value of eps. \end{DoxyCompactList}\item {\footnotesize template$<$typename Input\+Type , typename Target\+Type $>$ }\\Input\+Data\+Type\+::elem\+\_\+type \textbf{ Forward} (const Input\+Type \&input, const Target\+Type \&target) \begin{DoxyCompactList}\small\item\em Computes the Poisson negative log likelihood Loss. \end{DoxyCompactList}\item bool \textbf{ Full} () const \begin{DoxyCompactList}\small\item\em Get the value of full. \end{DoxyCompactList}\item bool \& \textbf{ Full} () \begin{DoxyCompactList}\small\item\em Modify the value of full. \end{DoxyCompactList}\item Input\+Data\+Type \& \textbf{ Input\+Parameter} () const \begin{DoxyCompactList}\small\item\em Get the input parameter. \end{DoxyCompactList}\item Input\+Data\+Type \& \textbf{ Input\+Parameter} () \begin{DoxyCompactList}\small\item\em Modify the input parameter. \end{DoxyCompactList}\item bool \textbf{ Log\+Input} () const \begin{DoxyCompactList}\small\item\em Get the value of log\+Input. \end{DoxyCompactList}\item bool \& \textbf{ Log\+Input} () \begin{DoxyCompactList}\small\item\em Modify the value of log\+Input. \end{DoxyCompactList}\item bool \textbf{ Mean} () const \begin{DoxyCompactList}\small\item\em Get the value of mean. \end{DoxyCompactList}\item bool \& \textbf{ Mean} () \begin{DoxyCompactList}\small\item\em Modify the value of mean. \end{DoxyCompactList}\item Output\+Data\+Type \& \textbf{ Output\+Parameter} () const \begin{DoxyCompactList}\small\item\em Get the output parameter. \end{DoxyCompactList}\item Output\+Data\+Type \& \textbf{ Output\+Parameter} () \begin{DoxyCompactList}\small\item\em Modify the output parameter. \end{DoxyCompactList}\item {\footnotesize template$<$typename Archive $>$ }\\void \textbf{ serialize} (Archive \&ar, const unsigned int) \begin{DoxyCompactList}\small\item\em Serialize the layer. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Input\+Data\+Type = arma\+::mat, typename Output\+Data\+Type = arma\+::mat$>$\newline class mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$} Implementation of the Poisson negative log likelihood loss. This loss function expects input for each class. It also expects a class index, in the range between 1 and the number of classes, as target when calling the Forward function. \begin{DoxyTemplParams}{Template Parameters} {\em Input\+Data\+Type} & Type of the input data (arma\+::colvec, arma\+::mat, arma\+::sp\+\_\+mat or arma\+::cube). \\ \hline {\em Output\+Data\+Type} & Type of the output data (arma\+::colvec, arma\+::mat, arma\+::sp\+\_\+mat or arma\+::cube). \\ \hline \end{DoxyTemplParams} Definition at line 36 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_a5865e4aed39aa2b2bab1dc3986c17bad}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Poisson\+N\+L\+L\+Loss@{Poisson\+N\+L\+L\+Loss}} \index{Poisson\+N\+L\+L\+Loss@{Poisson\+N\+L\+L\+Loss}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Poisson\+N\+L\+L\+Loss()} {\footnotesize\ttfamily \textbf{ Poisson\+N\+L\+L\+Loss} (\begin{DoxyParamCaption}\item[{const bool}]{log\+Input = {\ttfamily true}, }\item[{const bool}]{full = {\ttfamily false}, }\item[{const typename Input\+Data\+Type\+::elem\+\_\+type}]{eps = {\ttfamily 1e-\/08}, }\item[{const bool}]{mean = {\ttfamily true} }\end{DoxyParamCaption})} Create the \doxyref{Poisson\+N\+L\+L\+Loss}{p.}{classmlpack_1_1ann_1_1PoissonNLLLoss} object. \begin{DoxyParams}{Parameters} {\em log\+Input} & If true the loss is computed as $ \exp(input) - target \cdot input $, if false then the loss is $ input - target \cdot \log(input + eps) $. \\ \hline {\em full} & Boolean value that determines whether to include Stirling\textquotesingle{}s approximation term. \\ \hline {\em eps} & A small value to prevent 0 in denominators and logarithms. \\ \hline {\em mean} & When true, mean loss is computed otherwise total loss. \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_a7a5e88245fe9cf5644f846902393e97a}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Backward()} {\footnotesize\ttfamily void Backward (\begin{DoxyParamCaption}\item[{const Input\+Type \&}]{input, }\item[{const Target\+Type \&}]{target, }\item[{Output\+Type \&}]{output }\end{DoxyParamCaption})} Ordinary feed backward pass of a neural network. The Poisson Negative \doxyref{Log}{p.}{classmlpack_1_1Log} Likelihood loss function expects the input for each class. It expects a class index, in the range between 1 and the number of classes, as target when calling the Forward function. \begin{DoxyParams}{Parameters} {\em input} & The propagated input activation. \\ \hline {\em target} & The target vector, that contains the class index in the range between 1 and the number of classes. \\ \hline {\em output} & The calculated error. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_ab05635563f993b63975c8b908c2d7ee0}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Eps@{Eps}} \index{Eps@{Eps}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Eps()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Input\+Data\+Type\+::elem\+\_\+type Eps (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the value of eps. eps is a small value required to prevent 0 in logarithms and denominators. Definition at line 108 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_a69f7617ebeb301d9bef61a7a0be364c0}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Eps@{Eps}} \index{Eps@{Eps}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Eps()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Input\+Data\+Type\+::elem\+\_\+type\& Eps (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the value of eps. eps is a small value required to prevent 0 in logarithms and denominators. Definition at line 111 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_a0be49e57f181f39e4915ab47b880010e}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Forward()} {\footnotesize\ttfamily Input\+Data\+Type\+::elem\+\_\+type Forward (\begin{DoxyParamCaption}\item[{const Input\+Type \&}]{input, }\item[{const Target\+Type \&}]{target }\end{DoxyParamCaption})} Computes the Poisson negative log likelihood Loss. \begin{DoxyParams}{Parameters} {\em input} & Input data used for evaluating the specified function. \\ \hline {\em target} & The target vector, that contains the class index in the range between 1 and the number of classes. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_ac98e449411de44d49685058319efc65e}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Full@{Full}} \index{Full@{Full}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Full()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily bool Full (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the value of full. full is a boolean value that determines whether to include Stirling\textquotesingle{}s approximation term. Definition at line 101 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_adfe203f7f5637e67ec07731c514cde34}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Full@{Full}} \index{Full@{Full}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Full()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily bool\& Full (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the value of full. full is a boolean value that determines whether to include Stirling\textquotesingle{}s approximation term. Definition at line 104 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_a1506936601ddae886088d2804623ca4b}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Input\+Parameter@{Input\+Parameter}} \index{Input\+Parameter@{Input\+Parameter}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Input\+Parameter()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Input\+Data\+Type\& Input\+Parameter (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the input parameter. Definition at line 83 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_a063c3b1053c7979a7dd2e7bbd2bf1f8a}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Input\+Parameter@{Input\+Parameter}} \index{Input\+Parameter@{Input\+Parameter}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Input\+Parameter()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Input\+Data\+Type\& Input\+Parameter (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the input parameter. Definition at line 85 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_a9267f964724129e144495c74e942651c}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Log\+Input@{Log\+Input}} \index{Log\+Input@{Log\+Input}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Log\+Input()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily bool Log\+Input (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the value of log\+Input. log\+Input is a boolean value that tells if logits are given as input. Definition at line 94 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_ae62d8090ee6dba2ecfc81eee0976c0e1}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Log\+Input@{Log\+Input}} \index{Log\+Input@{Log\+Input}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Log\+Input()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily bool\& Log\+Input (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the value of log\+Input. log\+Input is a boolean value that tells if logits are given as input. Definition at line 97 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_ab3fece30ee983f7dc98302bacde75efe}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Mean@{Mean}} \index{Mean@{Mean}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Mean()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily bool Mean (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the value of mean. It\textquotesingle{}s a boolean value that tells if mean of the total loss has to be taken. Definition at line 115 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_ab9d30d78fb30a243c70e8dd27a88bf49}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Mean@{Mean}} \index{Mean@{Mean}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Mean()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily bool\& Mean (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the value of mean. It\textquotesingle{}s a boolean value that tells if mean of the total loss has to be taken. Definition at line 118 of file poisson\+\_\+nll\+\_\+loss.\+hpp. References Log\+::\+Fatal, and Poisson\+N\+L\+L\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_a8bae962cc603d1cab8d80ec78f8d505d}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Output\+Parameter()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Output\+Data\+Type\& Output\+Parameter (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the output parameter. Definition at line 88 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_a21d5f745f02c709625a4ee0907f004a5}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{Output\+Parameter()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Output\+Data\+Type\& Output\+Parameter (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the output parameter. Definition at line 90 of file poisson\+\_\+nll\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1PoissonNLLLoss_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss@{mlpack\+::ann\+::\+Poisson\+N\+L\+L\+Loss}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the layer. Referenced by Poisson\+N\+L\+L\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::\+Mean(). The documentation for this class was generated from the following file\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/git/src/mlpack/methods/ann/loss\+\_\+functions/\textbf{ poisson\+\_\+nll\+\_\+loss.\+hpp}\end{DoxyCompactItemize}