\section{Weight\+Norm$<$ Input\+Data\+Type, Output\+Data\+Type, Custom\+Layers $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1WeightNorm}\index{Weight\+Norm$<$ Input\+Data\+Type, Output\+Data\+Type, Custom\+Layers $>$@{Weight\+Norm$<$ Input\+Data\+Type, Output\+Data\+Type, Custom\+Layers $>$}} Declaration of the \doxyref{Weight\+Norm}{p.}{classmlpack_1_1ann_1_1WeightNorm} layer class. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Weight\+Norm} (\textbf{ Layer\+Types}$<$ Custom\+Layers... $>$ layer=\textbf{ Layer\+Types}$<$ Custom\+Layers... $>$()) \begin{DoxyCompactList}\small\item\em Create the \doxyref{Weight\+Norm}{p.}{classmlpack_1_1ann_1_1WeightNorm} layer object. \end{DoxyCompactList}\item \textbf{ $\sim$\+Weight\+Norm} () \begin{DoxyCompactList}\small\item\em Destructor to release allocated memory. \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 Backward pass through the layer. \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 Forward pass of the \doxyref{Weight\+Norm}{p.}{classmlpack_1_1ann_1_1WeightNorm} layer. \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, input activations and the weights of the wrapped layer. \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 \textbf{ Layer\+Types}$<$ Custom\+Layers... $>$ const \& \textbf{ Layer} () \begin{DoxyCompactList}\small\item\em Get the wrapped layer. \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}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Input\+Data\+Type = arma\+::mat, typename Output\+Data\+Type = arma\+::mat, typename... Custom\+Layers$>$\newline class mlpack\+::ann\+::\+Weight\+Norm$<$ Input\+Data\+Type, Output\+Data\+Type, Custom\+Layers $>$} Declaration of the \doxyref{Weight\+Norm}{p.}{classmlpack_1_1ann_1_1WeightNorm} layer class. The layer reparameterizes the weight vectors in a neural network, decoupling the length of those weight vectors from their direction. This reparameterization does not introduce any dependencies between the examples in a mini-\/batch. This class will be a wrapper around existing layers. It will just modify the calculation and updation of weights of the layer. For more information, refer to the following paper, \begin{DoxyCode} @inproceedings\{Salimans2016WeightNorm, title = \{Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks\}, author = \{Tim Salimans, Diederik P. Kingma\}, booktitle = \{Neural Information Processing Systems 2016\}, year = \{2016\}, url = \{https:\textcolor{comment}{//arxiv.org/abs/1602.07868\},} \} \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 {\em Custom\+Layers} & Additional custom layers that can be added. \\ \hline \end{DoxyTemplParams} Definition at line 208 of file layer\+\_\+types.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a02a0e3125b71703e2bbd9f7c4a885f48}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Weight\+Norm@{Weight\+Norm}} \index{Weight\+Norm@{Weight\+Norm}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \subsubsection{Weight\+Norm()} {\footnotesize\ttfamily \textbf{ Weight\+Norm} (\begin{DoxyParamCaption}\item[{\textbf{ Layer\+Types}$<$ Custom\+Layers... $>$}]{layer = {\ttfamily \textbf{ Layer\+Types}$<$~CustomLayers...~$>$()} }\end{DoxyParamCaption})} Create the \doxyref{Weight\+Norm}{p.}{classmlpack_1_1ann_1_1WeightNorm} layer object. \begin{DoxyParams}{Parameters} {\em layer} & The layer whose weights are needed to be normalized. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a7a39b4b1598f10f975e148d58591af59}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!````~Weight\+Norm@{$\sim$\+Weight\+Norm}} \index{````~Weight\+Norm@{$\sim$\+Weight\+Norm}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \subsubsection{$\sim$\+Weight\+Norm()} {\footnotesize\ttfamily $\sim$\textbf{ Weight\+Norm} (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Destructor to release allocated memory. \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a78dbad83871f43db1975e45a9a69c376}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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})} Backward pass through the layer. This function calls the \doxyref{Backward()}{p.}{classmlpack_1_1ann_1_1WeightNorm_a78dbad83871f43db1975e45a9a69c376} function of the wrapped layer. \begin{DoxyParams}{Parameters} {\em input} & The input activations. \\ \hline {\em gy} & The backpropagated error. \\ \hline {\em g} & The calculated gradient. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a797f7edb44dd081e5e2b3cc316eef6bd}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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 118 of file weight\+\_\+norm.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_ad6601342d560219ce951d554e69e5e87}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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 120 of file weight\+\_\+norm.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a461f849bc638c15bec262dc9c3a58abe}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \subsubsection{Forward()} {\footnotesize\ttfamily void Forward (\begin{DoxyParamCaption}\item[{const arma\+::\+Mat$<$ eT $>$ \&}]{input, }\item[{arma\+::\+Mat$<$ eT $>$ \&}]{output }\end{DoxyParamCaption})} Forward pass of the \doxyref{Weight\+Norm}{p.}{classmlpack_1_1ann_1_1WeightNorm} layer. Calculates the weights of the wrapped layer from the parameter vector v and the scalar parameter g. It then calulates the output of the wrapped layer from the calculated weights. \begin{DoxyParams}{Parameters} {\em input} & Input data for the layer. \\ \hline {\em output} & Resulting output activations. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_aaf577db350e2130754490d8486fba215}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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, input activations and the weights of the wrapped layer. \begin{DoxyParams}{Parameters} {\em input} & The input activations. \\ \hline {\em error} & The calculated error. \\ \hline {\em gradient} & The calculated gradient. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a0f1f4e6d93472d83852731a96c8c3f59}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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 123 of file weight\+\_\+norm.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a19abce4739c3b0b658b612537e21956a}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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 125 of file weight\+\_\+norm.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a9a889774509f2391dfd9b68e7c6a67aa}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Layer@{Layer}} \index{Layer@{Layer}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \subsubsection{Layer()} {\footnotesize\ttfamily \textbf{ Layer\+Types}$<$Custom\+Layers...$>$ const\& Layer (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Get the wrapped layer. Definition at line 138 of file weight\+\_\+norm.\+hpp. References Weight\+Norm$<$ Input\+Data\+Type, Output\+Data\+Type, Custom\+Layers $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a0ee21c2a36e5abad1e7a9d5dd00849f9}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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 128 of file weight\+\_\+norm.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a21d5f745f02c709625a4ee0907f004a5}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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 130 of file weight\+\_\+norm.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_aa530552c7ef915c952fbacc77b965c90}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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 133 of file weight\+\_\+norm.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a9c5c5900772a689d5a6b59778ec67120}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \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 135 of file weight\+\_\+norm.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_a372de693ad40b3f42839c8ec6ac845f4}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!Reset@{Reset}} \index{Reset@{Reset}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \subsubsection{Reset()} {\footnotesize\ttfamily void Reset (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Reset the layer parameters. \mbox{\label{classmlpack_1_1ann_1_1WeightNorm_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+Weight\+Norm@{mlpack\+::ann\+::\+Weight\+Norm}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the layer. Referenced by Weight\+Norm$<$ Input\+Data\+Type, Output\+Data\+Type, Custom\+Layers $>$\+::\+Layer(). 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{ weight\+\_\+norm.\+hpp}\end{DoxyCompactItemize}