\section{Recurrent\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1RecurrentAttention}\index{Recurrent\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type $>$@{Recurrent\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type $>$}} This class implements the \doxyref{Recurrent}{p.}{classmlpack_1_1ann_1_1Recurrent} Model for Visual Attention, using a variety of possible layer implementations. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Recurrent\+Attention} () \begin{DoxyCompactList}\small\item\em Default constructor\+: this will not give a usable \doxyref{Recurrent\+Attention}{p.}{classmlpack_1_1ann_1_1RecurrentAttention} object, so be sure to set all the parameters before use. \end{DoxyCompactList}\item {\footnotesize template$<$typename R\+N\+N\+Module\+Type , typename Action\+Module\+Type $>$ }\\\textbf{ Recurrent\+Attention} (const size\+\_\+t out\+Size, const R\+N\+N\+Module\+Type \&rnn, const Action\+Module\+Type \&action, const size\+\_\+t rho) \begin{DoxyCompactList}\small\item\em Create the \doxyref{Recurrent\+Attention}{p.}{classmlpack_1_1ann_1_1RecurrentAttention} object using the specified modules. \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 bool \textbf{ Deterministic} () const \begin{DoxyCompactList}\small\item\em The value of the deterministic parameter. \end{DoxyCompactList}\item bool \& \textbf{ Deterministic} () \begin{DoxyCompactList}\small\item\em Modify the value of the deterministic parameter. \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 $>$ \&, const arma\+::\+Mat$<$ eT $>$ \&, arma\+::\+Mat$<$ eT $>$ \&) \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 std\+::vector$<$ \textbf{ Layer\+Types}$<$$>$ $>$ \& \textbf{ Model} () \begin{DoxyCompactList}\small\item\em Get the model modules. \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 {\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\+::\+Recurrent\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type $>$} This class implements the \doxyref{Recurrent}{p.}{classmlpack_1_1ann_1_1Recurrent} Model for Visual Attention, using a variety of possible layer implementations. For more information, see the following paper. \begin{DoxyCode} @article\{MnihHGK14, title = \{Recurrent Models of Visual Attention\}, author = \{Volodymyr Mnih, Nicolas Heess, Alex Graves, Koray Kavukcuoglu\}, journal = \{CoRR\}, volume = \{abs/1406.6247\}, year = \{2014\}, url = \{https:\textcolor{comment}{//arxiv.org/abs/1406.6247\}} \} \end{DoxyCode} \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 168 of file layer\+\_\+types.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a22ed8f5cdffdce22f47f8f3768e19a47}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Recurrent\+Attention@{Recurrent\+Attention}} \index{Recurrent\+Attention@{Recurrent\+Attention}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}} \subsubsection{Recurrent\+Attention()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily \textbf{ Recurrent\+Attention} (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Default constructor\+: this will not give a usable \doxyref{Recurrent\+Attention}{p.}{classmlpack_1_1ann_1_1RecurrentAttention} object, so be sure to set all the parameters before use. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a8cc232af21a0e198cc6dc88366d86f02}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Recurrent\+Attention@{Recurrent\+Attention}} \index{Recurrent\+Attention@{Recurrent\+Attention}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}} \subsubsection{Recurrent\+Attention()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily \textbf{ Recurrent\+Attention} (\begin{DoxyParamCaption}\item[{const size\+\_\+t}]{out\+Size, }\item[{const R\+N\+N\+Module\+Type \&}]{rnn, }\item[{const Action\+Module\+Type \&}]{action, }\item[{const size\+\_\+t}]{rho }\end{DoxyParamCaption})} Create the \doxyref{Recurrent\+Attention}{p.}{classmlpack_1_1ann_1_1RecurrentAttention} object using the specified modules. \begin{DoxyParams}{Parameters} {\em out\+Size} & The module output size. \\ \hline {\em rnn} & The recurrent neural network module. \\ \hline {\em action} & The action module. \\ \hline {\em rho} & Maximum number of steps to backpropagate through time (B\+P\+TT). \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_ad9ad1a3bdb0f3fff5c839ed155e4bbf8}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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 input} & The propagated input activation. \\ \hline {\em gy} & The backpropagated error. \\ \hline {\em g} & The calculated gradient. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a797f7edb44dd081e5e2b3cc316eef6bd}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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 134 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_ad6601342d560219ce951d554e69e5e87}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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 136 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a9f4103707f4d199ce5594d239b60443e}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Deterministic@{Deterministic}} \index{Deterministic@{Deterministic}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}} \subsubsection{Deterministic()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily bool Deterministic (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} The value of the deterministic parameter. Definition at line 119 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a42d4ee3da432cff20d3a41b8b1ec801c}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Deterministic@{Deterministic}} \index{Deterministic@{Deterministic}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}} \subsubsection{Deterministic()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily bool\& Deterministic (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the value of the deterministic parameter. Definition at line 121 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a461f849bc638c15bec262dc9c3a58abe}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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} & Input data used for evaluating the specified function. \\ \hline {\em output} & Resulting output activation. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_acb03ff976cc8ebe5bd829ff21f4a4258}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}} \subsubsection{Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily void Gradient (\begin{DoxyParamCaption}\item[{const arma\+::\+Mat$<$ eT $>$ \&}]{, }\item[{const arma\+::\+Mat$<$ eT $>$ \&}]{, }\item[{arma\+::\+Mat$<$ eT $>$ \&}]{ }\end{DoxyParamCaption})} \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a0f1f4e6d93472d83852731a96c8c3f59}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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 139 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a19abce4739c3b0b658b612537e21956a}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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 141 of file recurrent\+\_\+attention.\+hpp. References Recurrent\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a50c707b4f7c009339d8d661539baf38f}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Model@{Model}} \index{Model@{Model}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}} \subsubsection{Model()} {\footnotesize\ttfamily std\+::vector$<$\textbf{ Layer\+Types}$<$$>$ $>$\& Model (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Get the model modules. Definition at line 116 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a0ee21c2a36e5abad1e7a9d5dd00849f9}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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 129 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a21d5f745f02c709625a4ee0907f004a5}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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 131 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_aa530552c7ef915c952fbacc77b965c90}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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 124 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_a9c5c5900772a689d5a6b59778ec67120}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+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 126 of file recurrent\+\_\+attention.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1RecurrentAttention_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+Recurrent\+Attention@{mlpack\+::ann\+::\+Recurrent\+Attention}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the layer. Referenced by Recurrent\+Attention$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::\+Gradient(). The documentation for this class was generated from the following files\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/3.\+3.\+0/src/mlpack/methods/ann/layer/\textbf{ layer\+\_\+types.\+hpp}\item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/3.\+3.\+0/src/mlpack/methods/ann/layer/\textbf{ recurrent\+\_\+attention.\+hpp}\end{DoxyCompactItemize}