\section{Multihead\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type, Regularizer\+Type $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1MultiheadAttention}\index{Multihead\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type, Regularizer\+Type $>$@{Multihead\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type, Regularizer\+Type $>$}} Multihead Attention allows the model to jointly attend to information from different representation subspaces at different positions. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Multihead\+Attention} () \begin{DoxyCompactList}\small\item\em Default constructor. \end{DoxyCompactList}\item \textbf{ Multihead\+Attention} (const size\+\_\+t tgt\+Seq\+Len, const size\+\_\+t src\+Seq\+Len, const size\+\_\+t embed\+Dim, const size\+\_\+t num\+Heads) \begin{DoxyCompactList}\small\item\em Create the \doxyref{Multihead\+Attention}{p.}{classmlpack_1_1ann_1_1MultiheadAttention} object using the specified modules. \end{DoxyCompactList}\item Output\+Data\+Type const \& \textbf{ Attention\+Mask} () const \begin{DoxyCompactList}\small\item\em Get the two dimensional Attention Mask. \end{DoxyCompactList}\item Output\+Data\+Type \& \textbf{ Attention\+Mask} () \begin{DoxyCompactList}\small\item\em Modify the two dimensional Attention Mask. \end{DoxyCompactList}\item {\footnotesize template$<$typename eT $>$ }\\void \textbf{ Backward} (const arma\+::\+Mat$<$ eT $>$ \&, const arma\+::\+Mat$<$ eT $>$ \&gy, arma\+::\+Mat$<$ eT $>$ \&g) \begin{DoxyCompactList}\small\item\em Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f. \end{DoxyCompactList}\item Output\+Data\+Type const \& \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 size\+\_\+t \textbf{ Embed\+Dim} () const \begin{DoxyCompactList}\small\item\em Get the embedding dimension. \end{DoxyCompactList}\item size\+\_\+t \& \textbf{ Embed\+Dim} () \begin{DoxyCompactList}\small\item\em Modify the embedding dimension. \end{DoxyCompactList}\item {\footnotesize template$<$typename eT $>$ }\\void \textbf{ Forward} (const arma\+::\+Mat$<$ eT $>$ \&input, arma\+::\+Mat$<$ eT $>$ \&output) \begin{DoxyCompactList}\small\item\em Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. \end{DoxyCompactList}\item {\footnotesize template$<$typename eT $>$ }\\void \textbf{ Gradient} (const arma\+::\+Mat$<$ eT $>$ \&input, const arma\+::\+Mat$<$ eT $>$ \&error, arma\+::\+Mat$<$ eT $>$ \&gradient) \begin{DoxyCompactList}\small\item\em Calculate the gradient using the output delta and the input activation. \end{DoxyCompactList}\item Output\+Data\+Type const \& \textbf{ Gradient} () const \begin{DoxyCompactList}\small\item\em Get the gradient. \end{DoxyCompactList}\item Output\+Data\+Type \& \textbf{ Gradient} () \begin{DoxyCompactList}\small\item\em Modify the gradient. \end{DoxyCompactList}\item Output\+Data\+Type const \& \textbf{ Key\+Padding\+Mask} () const \begin{DoxyCompactList}\small\item\em Get Key \doxyref{Padding}{p.}{classmlpack_1_1ann_1_1Padding} Mask. \end{DoxyCompactList}\item Output\+Data\+Type \& \textbf{ Key\+Padding\+Mask} () \begin{DoxyCompactList}\small\item\em Modify the Key \doxyref{Padding}{p.}{classmlpack_1_1ann_1_1Padding} Mask. \end{DoxyCompactList}\item size\+\_\+t \textbf{ Num\+Heads} () const \begin{DoxyCompactList}\small\item\em Get the number of attention heads. \end{DoxyCompactList}\item size\+\_\+t \& \textbf{ Num\+Heads} () \begin{DoxyCompactList}\small\item\em Modify the number of attention heads. \end{DoxyCompactList}\item Output\+Data\+Type const \& \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 Output\+Data\+Type const \& \textbf{ Parameters} () const \begin{DoxyCompactList}\small\item\em Get the parameters. \end{DoxyCompactList}\item Output\+Data\+Type \& \textbf{ Parameters} () \begin{DoxyCompactList}\small\item\em Modify the parameters. \end{DoxyCompactList}\item void \textbf{ Reset} () \begin{DoxyCompactList}\small\item\em Reset the layer parameters. \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 size\+\_\+t \textbf{ Src\+Seq\+Len} () const \begin{DoxyCompactList}\small\item\em Get the source sequence length. \end{DoxyCompactList}\item size\+\_\+t \& \textbf{ Src\+Seq\+Len} () \begin{DoxyCompactList}\small\item\em Modify the source sequence length. \end{DoxyCompactList}\item size\+\_\+t \textbf{ Tgt\+Seq\+Len} () const \begin{DoxyCompactList}\small\item\em Get the target sequence length. \end{DoxyCompactList}\item size\+\_\+t \& \textbf{ Tgt\+Seq\+Len} () \begin{DoxyCompactList}\small\item\em Modify the target sequence length. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Input\+Data\+Type = arma\+::mat, typename Output\+Data\+Type = arma\+::mat, typename Regularizer\+Type = No\+Regularizer$>$\newline class mlpack\+::ann\+::\+Multihead\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type, Regularizer\+Type $>$} Multihead Attention allows the model to jointly attend to information from different representation subspaces at different positions. With a single attention head, averaging inhibits this. [arxiv.\+org\+:1706.\+03762v5] The \doxyref{Multihead\+Attention}{p.}{classmlpack_1_1ann_1_1MultiheadAttention} class takes concatenated form of query, key and value. The query, key and value are concatenated into single matrix and fed to the Forward function as input. The query, key and value are matrices of shapes {\ttfamily (embed\+Dim $\ast$ tgt\+Seq\+Len, batch\+Size)}, {\ttfamily (embed\+Dim $\ast$ src\+Seq\+Len, batch\+Size)} and {\ttfamily (embed\+Dim $\ast$ src\+Seq\+Len, batch\+Size)} respectively. The output is a matrix of shape {\ttfamily (embed\+Dim $\ast$ tgt\+Seq\+Len, batch\+Size)}. The embeddings are stored consequently. \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 {\em Regularizer\+Type} & Type of the regularizer to be used. \\ \hline \end{DoxyTemplParams} Definition at line 120 of file layer\+\_\+types.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a89e14f85a9e6aadadb8957a2d584dad3}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Multihead\+Attention@{Multihead\+Attention}} \index{Multihead\+Attention@{Multihead\+Attention}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Multihead\+Attention()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily \textbf{ Multihead\+Attention} (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Default constructor. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_aafa325315a5c882251a0203e22fa2278}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Multihead\+Attention@{Multihead\+Attention}} \index{Multihead\+Attention@{Multihead\+Attention}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Multihead\+Attention()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily \textbf{ Multihead\+Attention} (\begin{DoxyParamCaption}\item[{const size\+\_\+t}]{tgt\+Seq\+Len, }\item[{const size\+\_\+t}]{src\+Seq\+Len, }\item[{const size\+\_\+t}]{embed\+Dim, }\item[{const size\+\_\+t}]{num\+Heads }\end{DoxyParamCaption})} Create the \doxyref{Multihead\+Attention}{p.}{classmlpack_1_1ann_1_1MultiheadAttention} object using the specified modules. \begin{DoxyParams}{Parameters} {\em tgt\+Seq\+Len} & Target sequence length. \\ \hline {\em src\+Seq\+Len} & Source sequence length. \\ \hline {\em embed\+Dim} & Total dimension of the model. \\ \hline {\em num\+Heads} & Number of parallel attention heads. \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a89e570724e353838afd7e6a5bf9ff56c}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Attention\+Mask@{Attention\+Mask}} \index{Attention\+Mask@{Attention\+Mask}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Attention\+Mask()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Output\+Data\+Type const\& Attention\+Mask (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the two dimensional Attention Mask. Definition at line 150 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a522e4242ea373d4ceae12bd644a304a1}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Attention\+Mask@{Attention\+Mask}} \index{Attention\+Mask@{Attention\+Mask}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Attention\+Mask()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Output\+Data\+Type\& Attention\+Mask (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the two dimensional Attention Mask. Definition at line 152 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_ad9ad1a3bdb0f3fff5c839ed155e4bbf8}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Backward()} {\footnotesize\ttfamily void Backward (\begin{DoxyParamCaption}\item[{const arma\+::\+Mat$<$ eT $>$ \&}]{, }\item[{const arma\+::\+Mat$<$ eT $>$ \&}]{gy, }\item[{arma\+::\+Mat$<$ eT $>$ \&}]{g }\end{DoxyParamCaption})} Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f. Using the results from the feed forward pass. \begin{DoxyParams}{Parameters} {\em gy} & The backpropagated error. \\ \hline {\em g} & The calculated gradient. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a797f7edb44dd081e5e2b3cc316eef6bd}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Delta()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Output\+Data\+Type const\& Delta (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the delta. Definition at line 165 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_ad6601342d560219ce951d554e69e5e87}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \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 167 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_acecd447ab68e6adb9e08fc90c2626d7f}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Embed\+Dim@{Embed\+Dim}} \index{Embed\+Dim@{Embed\+Dim}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Embed\+Dim()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily size\+\_\+t Embed\+Dim (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the embedding dimension. Definition at line 140 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_aa3ae45e06e75b0ccbc2ef9a17af2a7e3}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Embed\+Dim@{Embed\+Dim}} \index{Embed\+Dim@{Embed\+Dim}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Embed\+Dim()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily size\+\_\+t\& Embed\+Dim (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the embedding dimension. Definition at line 142 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a461f849bc638c15bec262dc9c3a58abe}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Forward()} {\footnotesize\ttfamily void Forward (\begin{DoxyParamCaption}\item[{const arma\+::\+Mat$<$ eT $>$ \&}]{input, }\item[{arma\+::\+Mat$<$ eT $>$ \&}]{output }\end{DoxyParamCaption})} Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. \begin{DoxyParams}{Parameters} {\em input} & The query matrix. \\ \hline {\em output} & Resulting output activation. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_aaf577db350e2130754490d8486fba215}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily void Gradient (\begin{DoxyParamCaption}\item[{const arma\+::\+Mat$<$ eT $>$ \&}]{input, }\item[{const arma\+::\+Mat$<$ eT $>$ \&}]{error, }\item[{arma\+::\+Mat$<$ eT $>$ \&}]{gradient }\end{DoxyParamCaption})} Calculate the gradient using the output delta and the input activation. \begin{DoxyParams}{Parameters} {\em input} & The input data used for evaluating specified function. \\ \hline {\em error} & The calculated error. \\ \hline {\em gradient} & The calculated gradient. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a0f1f4e6d93472d83852731a96c8c3f59}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [2/3]}} {\footnotesize\ttfamily Output\+Data\+Type const\& Gradient (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the gradient. Definition at line 170 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a19abce4739c3b0b658b612537e21956a}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [3/3]}} {\footnotesize\ttfamily Output\+Data\+Type\& Gradient (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the gradient. Definition at line 172 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a0fd1f2b59697e938c99921a7409fe199}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Key\+Padding\+Mask@{Key\+Padding\+Mask}} \index{Key\+Padding\+Mask@{Key\+Padding\+Mask}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Key\+Padding\+Mask()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Output\+Data\+Type const\& Key\+Padding\+Mask (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get Key \doxyref{Padding}{p.}{classmlpack_1_1ann_1_1Padding} Mask. Definition at line 155 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a8d09888b345cc0b543f8e45097b44450}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Key\+Padding\+Mask@{Key\+Padding\+Mask}} \index{Key\+Padding\+Mask@{Key\+Padding\+Mask}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Key\+Padding\+Mask()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Output\+Data\+Type\& Key\+Padding\+Mask (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the Key \doxyref{Padding}{p.}{classmlpack_1_1ann_1_1Padding} Mask. Definition at line 157 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a2a690c9f566cc397042a132e537d0c72}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Num\+Heads@{Num\+Heads}} \index{Num\+Heads@{Num\+Heads}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Num\+Heads()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily size\+\_\+t Num\+Heads (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the number of attention heads. Definition at line 145 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a5e4369c6d0a545d2e846a542bcbf6eb0}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Num\+Heads@{Num\+Heads}} \index{Num\+Heads@{Num\+Heads}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Num\+Heads()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily size\+\_\+t\& Num\+Heads (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the number of attention heads. Definition at line 147 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a0ee21c2a36e5abad1e7a9d5dd00849f9}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Output\+Parameter()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Output\+Data\+Type const\& Output\+Parameter (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the output parameter. Definition at line 160 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a21d5f745f02c709625a4ee0907f004a5}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \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 162 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_aa530552c7ef915c952fbacc77b965c90}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Parameters()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Output\+Data\+Type const\& Parameters (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the parameters. Definition at line 175 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a9c5c5900772a689d5a6b59778ec67120}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Parameters()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Output\+Data\+Type\& Parameters (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the parameters. Definition at line 177 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a372de693ad40b3f42839c8ec6ac845f4}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Reset@{Reset}} \index{Reset@{Reset}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Reset()} {\footnotesize\ttfamily void Reset (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Reset the layer parameters. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the layer. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_ae7ebd738697b221b93c9c52a9051778b}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Src\+Seq\+Len@{Src\+Seq\+Len}} \index{Src\+Seq\+Len@{Src\+Seq\+Len}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Src\+Seq\+Len()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily size\+\_\+t Src\+Seq\+Len (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the source sequence length. Definition at line 135 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a7a98480061115277dad0da34cf1a0fc6}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Src\+Seq\+Len@{Src\+Seq\+Len}} \index{Src\+Seq\+Len@{Src\+Seq\+Len}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Src\+Seq\+Len()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily size\+\_\+t\& Src\+Seq\+Len (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the source sequence length. Definition at line 137 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a31cae0a519246c1e5bb0157d8483c934}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Tgt\+Seq\+Len@{Tgt\+Seq\+Len}} \index{Tgt\+Seq\+Len@{Tgt\+Seq\+Len}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Tgt\+Seq\+Len()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily size\+\_\+t Tgt\+Seq\+Len (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the target sequence length. Definition at line 130 of file multihead\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1MultiheadAttention_a02b04b97b89fd1512b0b4af39630dae4}} \index{mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}!Tgt\+Seq\+Len@{Tgt\+Seq\+Len}} \index{Tgt\+Seq\+Len@{Tgt\+Seq\+Len}!mlpack\+::ann\+::\+Multihead\+Attention@{mlpack\+::ann\+::\+Multihead\+Attention}} \subsubsection{Tgt\+Seq\+Len()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily size\+\_\+t\& Tgt\+Seq\+Len (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the target sequence length. Definition at line 132 of file multihead\+\_\+attention.\+hpp. The documentation for this class was generated from the following files\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/git/src/mlpack/methods/ann/layer/\textbf{ layer\+\_\+types.\+hpp}\item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/git/src/mlpack/methods/ann/layer/\textbf{ multihead\+\_\+attention.\+hpp}\end{DoxyCompactItemize}