\section{Lookup$<$ Input\+Data\+Type, Output\+Data\+Type $>$ Class Template Reference}
\label{classmlpack_1_1ann_1_1Lookup}\index{Lookup$<$ Input\+Data\+Type, Output\+Data\+Type $>$@{Lookup$<$ Input\+Data\+Type, Output\+Data\+Type $>$}}


The \doxyref{Lookup}{p.}{classmlpack_1_1ann_1_1Lookup} class stores word embeddings and retrieves them using tokens.  


\subsection*{Public Member Functions}
\begin{DoxyCompactItemize}
\item 
\textbf{ Lookup} (const size\+\_\+t vocab\+Size=0, const size\+\_\+t embedding\+Size=0)
\begin{DoxyCompactList}\small\item\em Create the \doxyref{Lookup}{p.}{classmlpack_1_1ann_1_1Lookup} object using the specified vocabulary and embedding size. \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{ Embedding\+Size} () const
\begin{DoxyCompactList}\small\item\em Get the length of each embedding vector. \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{ 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}\item 
size\+\_\+t \textbf{ Vocab\+Size} () const
\begin{DoxyCompactList}\small\item\em Get the size of the vocabulary. \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\+::\+Lookup$<$ Input\+Data\+Type, Output\+Data\+Type $>$}

The \doxyref{Lookup}{p.}{classmlpack_1_1ann_1_1Lookup} class stores word embeddings and retrieves them using tokens. 

The \doxyref{Lookup}{p.}{classmlpack_1_1ann_1_1Lookup} layer is always the first layer of the network. The input to the \doxyref{Lookup}{p.}{classmlpack_1_1ann_1_1Lookup} class is a matrix of shape (sequence\+Length, batch\+Size). The matrix consists of tokens which are used to lookup the table (i.\+e. weights) to find the embeddings of those tokens.

The input shape \+: (sequence\+Length, batch\+Size). The output shape \+: (embedding\+Size, sequence\+Length, batch\+Size).


\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 41 of file lookup.\+hpp.



\subsection{Constructor \& Destructor Documentation}
\mbox{\label{classmlpack_1_1ann_1_1Lookup_ad2a92a24a6c38f608d103d2ac2153a91}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Lookup@{Lookup}}
\index{Lookup@{Lookup}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\subsubsection{Lookup()}
{\footnotesize\ttfamily \textbf{ Lookup} (\begin{DoxyParamCaption}\item[{const size\+\_\+t}]{vocab\+Size = {\ttfamily 0},  }\item[{const size\+\_\+t}]{embedding\+Size = {\ttfamily 0} }\end{DoxyParamCaption})}



Create the \doxyref{Lookup}{p.}{classmlpack_1_1ann_1_1Lookup} object using the specified vocabulary and embedding size. 


\begin{DoxyParams}{Parameters}
{\em vocab\+Size} & The size of the vocabulary. \\
\hline
{\em embedding\+Size} & The length of each embedding vector. \\
\hline
\end{DoxyParams}


\subsection{Member Function Documentation}
\mbox{\label{classmlpack_1_1ann_1_1Lookup_ad9ad1a3bdb0f3fff5c839ed155e4bbf8}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Backward@{Backward}}
\index{Backward@{Backward}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 $\ast$} & (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_1Lookup_a797f7edb44dd081e5e2b3cc316eef6bd}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Delta@{Delta}}
\index{Delta@{Delta}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 99 of file lookup.\+hpp.

\mbox{\label{classmlpack_1_1ann_1_1Lookup_ad6601342d560219ce951d554e69e5e87}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Delta@{Delta}}
\index{Delta@{Delta}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 101 of file lookup.\+hpp.

\mbox{\label{classmlpack_1_1ann_1_1Lookup_af901e8433309aa802f54ce6efdafe41b}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Embedding\+Size@{Embedding\+Size}}
\index{Embedding\+Size@{Embedding\+Size}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\subsubsection{Embedding\+Size()}
{\footnotesize\ttfamily size\+\_\+t Embedding\+Size (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}}



Get the length of each embedding vector. 



Definition at line 112 of file lookup.\+hpp.



References Lookup$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::serialize().

\mbox{\label{classmlpack_1_1ann_1_1Lookup_a461f849bc638c15bec262dc9c3a58abe}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Forward@{Forward}}
\index{Forward@{Forward}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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_1Lookup_aaf577db350e2130754490d8486fba215}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Gradient@{Gradient}}
\index{Gradient@{Gradient}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 parameter used for calculating the gradient. \\
\hline
{\em error} & The calculated error. \\
\hline
{\em gradient} & The calculated gradient. \\
\hline
\end{DoxyParams}
\mbox{\label{classmlpack_1_1ann_1_1Lookup_a0f1f4e6d93472d83852731a96c8c3f59}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Gradient@{Gradient}}
\index{Gradient@{Gradient}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 104 of file lookup.\+hpp.

\mbox{\label{classmlpack_1_1ann_1_1Lookup_a19abce4739c3b0b658b612537e21956a}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Gradient@{Gradient}}
\index{Gradient@{Gradient}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 106 of file lookup.\+hpp.

\mbox{\label{classmlpack_1_1ann_1_1Lookup_a0ee21c2a36e5abad1e7a9d5dd00849f9}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Output\+Parameter@{Output\+Parameter}}
\index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 94 of file lookup.\+hpp.

\mbox{\label{classmlpack_1_1ann_1_1Lookup_a21d5f745f02c709625a4ee0907f004a5}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Output\+Parameter@{Output\+Parameter}}
\index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 96 of file lookup.\+hpp.

\mbox{\label{classmlpack_1_1ann_1_1Lookup_aa530552c7ef915c952fbacc77b965c90}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Parameters@{Parameters}}
\index{Parameters@{Parameters}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 89 of file lookup.\+hpp.

\mbox{\label{classmlpack_1_1ann_1_1Lookup_a9c5c5900772a689d5a6b59778ec67120}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Parameters@{Parameters}}
\index{Parameters@{Parameters}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\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 91 of file lookup.\+hpp.

\mbox{\label{classmlpack_1_1ann_1_1Lookup_af0dd9205158ccf7bcfcd8ff81f79c927}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!serialize@{serialize}}
\index{serialize@{serialize}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\subsubsection{serialize()}
{\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar,  }\item[{const unsigned}]{int }\end{DoxyParamCaption})}



Serialize the layer. 



Referenced by Lookup$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::\+Embedding\+Size().

\mbox{\label{classmlpack_1_1ann_1_1Lookup_acc5c821b1d52424abca736bd81c3f476}} 
\index{mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}!Vocab\+Size@{Vocab\+Size}}
\index{Vocab\+Size@{Vocab\+Size}!mlpack\+::ann\+::\+Lookup@{mlpack\+::ann\+::\+Lookup}}
\subsubsection{Vocab\+Size()}
{\footnotesize\ttfamily size\+\_\+t Vocab\+Size (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}}



Get the size of the vocabulary. 



Definition at line 109 of file lookup.\+hpp.



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/layer/\textbf{ lookup.\+hpp}\end{DoxyCompactItemize}
