\section{Huber\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1HuberLoss}\index{Huber\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$@{Huber\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$}} The Huber loss is a loss function used in robust regression, that is less sensitive to outliers in data than the squared error loss. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Huber\+Loss} (const double delta=1.\+0, const bool mean=true) \begin{DoxyCompactList}\small\item\em Create the \doxyref{Huber\+Loss}{p.}{classmlpack_1_1ann_1_1HuberLoss} 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 double \textbf{ Delta} () const \begin{DoxyCompactList}\small\item\em Get the value of delta. \end{DoxyCompactList}\item double \& \textbf{ Delta} () \begin{DoxyCompactList}\small\item\em Set the value of delta. \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 Huber Loss function. \end{DoxyCompactList}\item bool \textbf{ Mean} () const \begin{DoxyCompactList}\small\item\em Get the value of reduction type. \end{DoxyCompactList}\item bool \& \textbf{ Mean} () \begin{DoxyCompactList}\small\item\em Set the value of reduction type. \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\+::\+Huber\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$} The Huber loss is a loss function used in robust regression, that is less sensitive to outliers in data than the squared error loss. This function is quadratic for small values of $ y - f(x) $, and linear for large values, with equal values and slopes of the different sections at the two points where $ |y - f(x)| = delta $. \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 huber\+\_\+loss.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1HuberLoss_af05212ee761a4171dcdd1d0065848bbb}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!Huber\+Loss@{Huber\+Loss}} \index{Huber\+Loss@{Huber\+Loss}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}} \subsubsection{Huber\+Loss()} {\footnotesize\ttfamily \textbf{ Huber\+Loss} (\begin{DoxyParamCaption}\item[{const double}]{delta = {\ttfamily 1.0}, }\item[{const bool}]{mean = {\ttfamily true} }\end{DoxyParamCaption})} Create the \doxyref{Huber\+Loss}{p.}{classmlpack_1_1ann_1_1HuberLoss} object. \begin{DoxyParams}{Parameters} {\em delta} & The threshold value upto which squared error is followed and after which absolute error is considered. \\ \hline {\em mean} & If true then mean loss is computed otherwise sum. \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1HuberLoss_a7a5e88245fe9cf5644f846902393e97a}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+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_1HuberLoss_acb1f7d73ed8ec9121d6d0e45b560d8fa}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}} \subsubsection{Delta()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double Delta (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the value of delta. Definition at line 76 of file huber\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HuberLoss_a9fcb8a5caa7165245d5aa803b0a94a7c}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}} \subsubsection{Delta()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily double\& Delta (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Set the value of delta. Definition at line 78 of file huber\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HuberLoss_aad9536a75d4ecfe220d313adc47f38fa}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+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 Huber Loss function. \begin{DoxyParams}{Parameters} {\em input} & Input data used for evaluating the specified function. \\ \hline {\em target} & The target vector. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1HuberLoss_ab3fece30ee983f7dc98302bacde75efe}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!Mean@{Mean}} \index{Mean@{Mean}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+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 reduction type. Definition at line 81 of file huber\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HuberLoss_ab9d30d78fb30a243c70e8dd27a88bf49}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!Mean@{Mean}} \index{Mean@{Mean}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}} \subsubsection{Mean()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily bool\& Mean (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Set the value of reduction type. Definition at line 83 of file huber\+\_\+loss.\+hpp. References Huber\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1HuberLoss_a8bae962cc603d1cab8d80ec78f8d505d}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+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 71 of file huber\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HuberLoss_a21d5f745f02c709625a4ee0907f004a5}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+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 73 of file huber\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HuberLoss_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+Huber\+Loss@{mlpack\+::ann\+::\+Huber\+Loss}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the layer. Referenced by Huber\+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{ huber\+\_\+loss.\+hpp}\end{DoxyCompactItemize}