\section{Cosine\+Embedding\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1CosineEmbeddingLoss}\index{Cosine\+Embedding\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$@{Cosine\+Embedding\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$}} Cosine Embedding Loss function is used for measuring whether two inputs are similar or dissimilar, using the cosine distance, and is typically used for learning nonlinear embeddings or semi-\/supervised learning. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Cosine\+Embedding\+Loss} (const double margin=0.\+0, const bool similarity=true, const bool take\+Mean=false) \begin{DoxyCompactList}\small\item\em Create the \doxyref{Cosine\+Embedding\+Loss}{p.}{classmlpack_1_1ann_1_1CosineEmbeddingLoss} 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 Output\+Data\+Type \& \textbf{ Delta} () const \begin{DoxyCompactList}\small\item\em Get the delta. \end{DoxyCompactList}\item Output\+Data\+Type \& \textbf{ Delta} () \begin{DoxyCompactList}\small\item\em Modify the 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 Ordinary feed forward pass of a neural network. \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 double \textbf{ Margin} () const \begin{DoxyCompactList}\small\item\em Get the value of margin. \end{DoxyCompactList}\item double \& \textbf{ Margin} () \begin{DoxyCompactList}\small\item\em Modify the value of take\+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}\item bool \textbf{ Similarity} () const \begin{DoxyCompactList}\small\item\em Get the value of similarity hyperparameter. \end{DoxyCompactList}\item bool \& \textbf{ Similarity} () \begin{DoxyCompactList}\small\item\em Modify the value of take\+Mean. \end{DoxyCompactList}\item bool \textbf{ Take\+Mean} () const \begin{DoxyCompactList}\small\item\em Get the value of take\+Mean. \end{DoxyCompactList}\item bool \& \textbf{ Take\+Mean} () \begin{DoxyCompactList}\small\item\em Modify the value of take\+Mean. \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\+::\+Cosine\+Embedding\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$} Cosine Embedding Loss function is used for measuring whether two inputs are similar or dissimilar, using the cosine distance, and is typically used for learning nonlinear embeddings or semi-\/supervised learning. \begin{eqnarray*} f(x) = 1 - cos(x1, x2) , for y = 1 f(x) = max(0, cos(x1, x2) - margin) , for y = -1 \end{eqnarray*} \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 39 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_a389938029e28bfa778819692fbb5f844}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Cosine\+Embedding\+Loss@{Cosine\+Embedding\+Loss}} \index{Cosine\+Embedding\+Loss@{Cosine\+Embedding\+Loss}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Cosine\+Embedding\+Loss()} {\footnotesize\ttfamily \textbf{ Cosine\+Embedding\+Loss} (\begin{DoxyParamCaption}\item[{const double}]{margin = {\ttfamily 0.0}, }\item[{const bool}]{similarity = {\ttfamily true}, }\item[{const bool}]{take\+Mean = {\ttfamily false} }\end{DoxyParamCaption})} Create the \doxyref{Cosine\+Embedding\+Loss}{p.}{classmlpack_1_1ann_1_1CosineEmbeddingLoss} object. \begin{DoxyParams}{Parameters} {\em margin} & Increases cosine distance in case of dissimilarity. Refer definition of cosine-\/embedding-\/loss above. \\ \hline {\em similarity} & Determines whether to use similarity or dissimilarity for comparision. \\ \hline {\em take\+Mean} & Boolean variable to specify whether to take mean or not. Specifies reduction method i.\+e. sum or mean corresponding to 0 and 1 respectively. Default value = 0. \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_a7a5e88245fe9cf5644f846902393e97a}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+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_1CosineEmbeddingLoss_ae7c8eba5764f021cd93e30efe638e63c}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Delta()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Output\+Data\+Type\& Delta (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the delta. Definition at line 90 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_ad6601342d560219ce951d554e69e5e87}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Delta()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Output\+Data\+Type\& Delta (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the delta. Definition at line 92 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_aad9536a75d4ecfe220d313adc47f38fa}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Forward()} {\footnotesize\ttfamily Input\+Type\+::elem\+\_\+type Forward (\begin{DoxyParamCaption}\item[{const Input\+Type \&}]{input, }\item[{const Target\+Type \&}]{target }\end{DoxyParamCaption})} Ordinary feed forward pass of a neural network. \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_1CosineEmbeddingLoss_a1506936601ddae886088d2804623ca4b}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Input\+Parameter@{Input\+Parameter}} \index{Input\+Parameter@{Input\+Parameter}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+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 80 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_a063c3b1053c7979a7dd2e7bbd2bf1f8a}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Input\+Parameter@{Input\+Parameter}} \index{Input\+Parameter@{Input\+Parameter}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+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 82 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_ac29c2c851ff367f45f9ec075352c5b83}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Margin@{Margin}} \index{Margin@{Margin}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Margin()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double Margin (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the value of margin. Definition at line 100 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_ab8c4d252f686cdc9c5972df28e65dcab}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Margin@{Margin}} \index{Margin@{Margin}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Margin()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily double\& Margin (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the value of take\+Mean. Definition at line 102 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_a8bae962cc603d1cab8d80ec78f8d505d}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+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 85 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_a21d5f745f02c709625a4ee0907f004a5}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+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 87 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the layer. Referenced by Cosine\+Embedding\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::\+Similarity(). \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_a92a76558ba5229079e8cb7c377f4cf67}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Similarity@{Similarity}} \index{Similarity@{Similarity}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Similarity()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily bool Similarity (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the value of similarity hyperparameter. Definition at line 105 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_a1e4d965a9c5f106922cbbeb52ba2111d}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Similarity@{Similarity}} \index{Similarity@{Similarity}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Similarity()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily bool\& Similarity (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the value of take\+Mean. Definition at line 107 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. References Cosine\+Embedding\+Loss$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_ab1afafdad2b04d3378dce6f13c9968a2}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Take\+Mean@{Take\+Mean}} \index{Take\+Mean@{Take\+Mean}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Take\+Mean()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily bool Take\+Mean (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the value of take\+Mean. Definition at line 95 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1CosineEmbeddingLoss_a6523d960bcd088ba1e86fbe2e095a79b}} \index{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}!Take\+Mean@{Take\+Mean}} \index{Take\+Mean@{Take\+Mean}!mlpack\+::ann\+::\+Cosine\+Embedding\+Loss@{mlpack\+::ann\+::\+Cosine\+Embedding\+Loss}} \subsubsection{Take\+Mean()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily bool\& Take\+Mean (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the value of take\+Mean. Definition at line 97 of file cosine\+\_\+embedding\+\_\+loss.\+hpp. 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.\+1/src/mlpack/methods/ann/loss\+\_\+functions/\textbf{ cosine\+\_\+embedding\+\_\+loss.\+hpp}\end{DoxyCompactItemize}