\section{Log\+Cosh\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1LogCoshLoss}\index{Log\+Cosh\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$@{Log\+Cosh\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$}} The Log-\/\+Hyperbolic-\/\+Cosine loss function is often used to improve variational auto encoder. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Log\+Cosh\+Loss} (const double a=1.\+0) \begin{DoxyCompactList}\small\item\em Create the Log-\/\+Hyperbolic-\/\+Cosine object with the specified parameters. \end{DoxyCompactList}\item double \textbf{ A} () const \begin{DoxyCompactList}\small\item\em Get the value of hyperparameter a. \end{DoxyCompactList}\item double \& \textbf{ A} () \begin{DoxyCompactList}\small\item\em Modify the value of hyperparameter a. \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 {\footnotesize template$<$typename Input\+Type , typename Target\+Type $>$ }\\Input\+Type\+::elem\+\_\+type \textbf{ Forward} (const Input\+Type \&input, const Target\+Type \&target) \begin{DoxyCompactList}\small\item\em Computes the Log-\/\+Hyperbolic-\/\+Cosine loss function. \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 loss function. \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\+::\+Log\+Cosh\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$} The Log-\/\+Hyperbolic-\/\+Cosine loss function is often used to improve variational auto encoder. This function is the log of hyperbolic cosine of difference between true values and predicted values. \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 35 of file log\+\_\+cosh\+\_\+loss.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1LogCoshLoss_aa786489fcdc270dd947b12eb8709c064}} \index{mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}!Log\+Cosh\+Loss@{Log\+Cosh\+Loss}} \index{Log\+Cosh\+Loss@{Log\+Cosh\+Loss}!mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}} \subsubsection{Log\+Cosh\+Loss()} {\footnotesize\ttfamily \textbf{ Log\+Cosh\+Loss} (\begin{DoxyParamCaption}\item[{const double}]{a = {\ttfamily 1.0} }\end{DoxyParamCaption})} Create the Log-\/\+Hyperbolic-\/\+Cosine object with the specified parameters. \begin{DoxyParams}{Parameters} {\em a} & A double type value for smoothening loss function. It must be positive a real number, Sharpness of loss function is directly proportional to a. It can also act as a scaling factor hence making the loss function more sensitive to small losses around the origin. Default value = 1.\+0. \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1LogCoshLoss_aab6c632054fc383ec1edf83231163bf7}} \index{mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}!A@{A}} \index{A@{A}!mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}} \subsubsection{A()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double A (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the value of hyperparameter a. Definition at line 79 of file log\+\_\+cosh\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1LogCoshLoss_ad9111aa092ab0ee1b38e0369657d2bfa}} \index{mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}!A@{A}} \index{A@{A}!mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}} \subsubsection{A()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily double\& A (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the value of hyperparameter a. Definition at line 81 of file log\+\_\+cosh\+\_\+loss.\+hpp. References Log\+Cosh\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1LogCoshLoss_a7a5e88245fe9cf5644f846902393e97a}} \index{mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+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. \begin{DoxyParams}{Parameters} {\em input} & The propagated input activation. \\ \hline {\em target} & The target vector. \\ \hline {\em output} & The calculated error. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1LogCoshLoss_aad9536a75d4ecfe220d313adc47f38fa}} \index{mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}} \subsubsection{Forward()} {\footnotesize\ttfamily Input\+Type\+::elem\+\_\+type Forward (\begin{DoxyParamCaption}\item[{const Input\+Type \&}]{input, }\item[{const Target\+Type \&}]{target }\end{DoxyParamCaption})} Computes the Log-\/\+Hyperbolic-\/\+Cosine loss function. \begin{DoxyParams}{Parameters} {\em input} & Input data used for evaluating the specified function. \\ \hline {\em target} & Target data to compare with. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1LogCoshLoss_a8bae962cc603d1cab8d80ec78f8d505d}} \index{mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+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 74 of file log\+\_\+cosh\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1LogCoshLoss_a21d5f745f02c709625a4ee0907f004a5}} \index{mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+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 76 of file log\+\_\+cosh\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1LogCoshLoss_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+Log\+Cosh\+Loss@{mlpack\+::ann\+::\+Log\+Cosh\+Loss}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the loss function. Referenced by Log\+Cosh\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::\+A(). The documentation for this class was generated from the following file\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/3.\+3.\+0/src/mlpack/methods/ann/loss\+\_\+functions/\textbf{ log\+\_\+cosh\+\_\+loss.\+hpp}\end{DoxyCompactItemize}