\section{Reparametrization$<$ Input\+Data\+Type, Output\+Data\+Type $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1Reparametrization}\index{Reparametrization$<$ Input\+Data\+Type, Output\+Data\+Type $>$@{Reparametrization$<$ Input\+Data\+Type, Output\+Data\+Type $>$}} Implementation of the \doxyref{Reparametrization}{p.}{classmlpack_1_1ann_1_1Reparametrization} layer class. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Reparametrization} () \begin{DoxyCompactList}\small\item\em Create the \doxyref{Reparametrization}{p.}{classmlpack_1_1ann_1_1Reparametrization} object. \end{DoxyCompactList}\item \textbf{ Reparametrization} (const size\+\_\+t latent\+Size, const bool stochastic=true, const bool include\+Kl=true, const double beta=1) \begin{DoxyCompactList}\small\item\em Create the \doxyref{Reparametrization}{p.}{classmlpack_1_1ann_1_1Reparametrization} layer object using the specified sample vector size. \end{DoxyCompactList}\item {\footnotesize template$<$typename eT $>$ }\\void \textbf{ Backward} (const arma\+::\+Mat$<$ eT $>$ \&input, 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 {\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 double \textbf{ Loss} () \begin{DoxyCompactList}\small\item\em Get the KL divergence with standard normal. \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 size\+\_\+t const \& \textbf{ Output\+Size} () const \begin{DoxyCompactList}\small\item\em Get the output size. \end{DoxyCompactList}\item size\+\_\+t \& \textbf{ Output\+Size} () \begin{DoxyCompactList}\small\item\em Modify the output size. \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\+::\+Reparametrization$<$ Input\+Data\+Type, Output\+Data\+Type $>$} Implementation of the \doxyref{Reparametrization}{p.}{classmlpack_1_1ann_1_1Reparametrization} layer class. This layer samples from the given parameters of a normal distribution. This class also supports beta-\/\+V\+AE, a state-\/of-\/the-\/art framework for automated discovery of interpretable factorised latent representations from raw image data in a completely unsupervised manner. For more information, refer the following paper. \begin{DoxyCode} @article\{ICLR2017, title = \{beta-VAE: Learning basic visual concepts with a constrained variational framework\}, author = \{Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed and Alexander Lerchner | Google DeepMind\}, journal = \{2017 International Conference on Learning Representations(ICLR)\}, year = \{2017\}, url = \{https:\textcolor{comment}{// deepmind.com/research/publications/beta-VAE-Learning-Basic-Visual-Concepts-with-a-Constrained-Variational-Framework\}} \} \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 97 of file layer\+\_\+types.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_a832fbcfd05acf9e46e104c51db19588f}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Reparametrization@{Reparametrization}} \index{Reparametrization@{Reparametrization}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \subsubsection{Reparametrization()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily \textbf{ Reparametrization} (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Create the \doxyref{Reparametrization}{p.}{classmlpack_1_1ann_1_1Reparametrization} object. \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_a4a8caf58b20566b71a6a9782211b8121}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Reparametrization@{Reparametrization}} \index{Reparametrization@{Reparametrization}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \subsubsection{Reparametrization()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily \textbf{ Reparametrization} (\begin{DoxyParamCaption}\item[{const size\+\_\+t}]{latent\+Size, }\item[{const bool}]{stochastic = {\ttfamily true}, }\item[{const bool}]{include\+Kl = {\ttfamily true}, }\item[{const double}]{beta = {\ttfamily 1} }\end{DoxyParamCaption})} Create the \doxyref{Reparametrization}{p.}{classmlpack_1_1ann_1_1Reparametrization} layer object using the specified sample vector size. \begin{DoxyParams}{Parameters} {\em latent\+Size} & The number of output latent units. \\ \hline {\em stochastic} & Whether we want random sample or constant. \\ \hline {\em include\+Kl} & Whether we want to include KL loss in backward function. \\ \hline {\em beta} & The beta (hyper)parameter for beta-\/\+V\+AE mentioned above. \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_a78dbad83871f43db1975e45a9a69c376}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \subsubsection{Backward()} {\footnotesize\ttfamily void Backward (\begin{DoxyParamCaption}\item[{const arma\+::\+Mat$<$ eT $>$ \&}]{input, }\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_1Reparametrization_a797f7edb44dd081e5e2b3cc316eef6bd}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \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 105 of file reparametrization.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_ad6601342d560219ce951d554e69e5e87}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \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 107 of file reparametrization.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_a461f849bc638c15bec262dc9c3a58abe}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \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_1Reparametrization_a97c2b4c73f25bb50e148d8e4febeda24}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Loss@{Loss}} \index{Loss@{Loss}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \subsubsection{Loss()} {\footnotesize\ttfamily double Loss (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Get the KL divergence with standard normal. Definition at line 115 of file reparametrization.\+hpp. References Reparametrization$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_a0ee21c2a36e5abad1e7a9d5dd00849f9}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \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 100 of file reparametrization.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_a21d5f745f02c709625a4ee0907f004a5}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \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 102 of file reparametrization.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_a004c01f91ccd1863b8df0ab76ab4aa6a}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Output\+Size@{Output\+Size}} \index{Output\+Size@{Output\+Size}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \subsubsection{Output\+Size()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily size\+\_\+t const\& Output\+Size (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the output size. Definition at line 110 of file reparametrization.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_a419dbf849d95d9955d055a2e6ba321d2}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!Output\+Size@{Output\+Size}} \index{Output\+Size@{Output\+Size}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \subsubsection{Output\+Size()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily size\+\_\+t\& Output\+Size (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the output size. Definition at line 112 of file reparametrization.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1Reparametrization_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+Reparametrization@{mlpack\+::ann\+::\+Reparametrization}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the layer. Referenced by Reparametrization$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::\+Loss(). 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{ reparametrization.\+hpp}\end{DoxyCompactItemize}