\section{F\+FN$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1FFN}\index{F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$@{F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$}} Implementation of a standard feed forward network. \subsection*{Public Types} \begin{DoxyCompactItemize} \item using \textbf{ Network\+Type} = \textbf{ F\+FN}$<$ Output\+Layer\+Type, Initialization\+Rule\+Type $>$ \begin{DoxyCompactList}\small\item\em Convenience typedef for the internal model construction. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ F\+FN} (Output\+Layer\+Type output\+Layer=Output\+Layer\+Type(), Initialization\+Rule\+Type initialize\+Rule=Initialization\+Rule\+Type()) \begin{DoxyCompactList}\small\item\em Create the \doxyref{F\+FN}{p.}{classmlpack_1_1ann_1_1FFN} object. \end{DoxyCompactList}\item \textbf{ F\+FN} (const \textbf{ F\+FN} \&) \begin{DoxyCompactList}\small\item\em Copy constructor. \end{DoxyCompactList}\item \textbf{ F\+FN} (\textbf{ F\+FN} \&\&) \begin{DoxyCompactList}\small\item\em Move constructor. \end{DoxyCompactList}\item \textbf{ $\sim$\+F\+FN} () \begin{DoxyCompactList}\small\item\em Destructor to release allocated memory. \end{DoxyCompactList}\item {\footnotesize template$<$class Layer\+Type , class... Args$>$ }\\void \textbf{ Add} (Args... args) \item void \textbf{ Add} (\textbf{ Layer\+Types}$<$ Custom\+Layers... $>$ layer) \item {\footnotesize template$<$typename Predictors\+Type , typename Targets\+Type , typename Gradients\+Type $>$ }\\double \textbf{ Backward} (const Predictors\+Type \&inputs, const Targets\+Type \&targets, Gradients\+Type \&gradients) \begin{DoxyCompactList}\small\item\em Perform the backward pass of the data in real batch mode. \end{DoxyCompactList}\item {\footnotesize template$<$typename Predictors\+Type , typename Responses\+Type $>$ }\\double \textbf{ Evaluate} (const Predictors\+Type \&predictors, const Responses\+Type \&responses) \begin{DoxyCompactList}\small\item\em Evaluate the feedforward network with the given predictors and responses. \end{DoxyCompactList}\item double \textbf{ Evaluate} (const arma\+::mat \¶meters) \begin{DoxyCompactList}\small\item\em Evaluate the feedforward network with the given parameters. \end{DoxyCompactList}\item double \textbf{ Evaluate} (const arma\+::mat \¶meters, const size\+\_\+t begin, const size\+\_\+t batch\+Size, const bool deterministic) \begin{DoxyCompactList}\small\item\em Evaluate the feedforward network with the given parameters, but using only a number of data points. \end{DoxyCompactList}\item double \textbf{ Evaluate} (const arma\+::mat \¶meters, const size\+\_\+t begin, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Evaluate the feedforward network with the given parameters, but using only a number of data points. \end{DoxyCompactList}\item {\footnotesize template$<$typename Grad\+Type $>$ }\\double \textbf{ Evaluate\+With\+Gradient} (const arma\+::mat \¶meters, Grad\+Type \&gradient) \begin{DoxyCompactList}\small\item\em Evaluate the feedforward network with the given parameters. \end{DoxyCompactList}\item {\footnotesize template$<$typename Grad\+Type $>$ }\\double \textbf{ Evaluate\+With\+Gradient} (const arma\+::mat \¶meters, const size\+\_\+t begin, Grad\+Type \&gradient, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Evaluate the feedforward network with the given parameters, but using only a number of data points. \end{DoxyCompactList}\item {\footnotesize template$<$typename Predictors\+Type , typename Responses\+Type $>$ }\\void \textbf{ Forward} (const Predictors\+Type \&inputs, Responses\+Type \&results) \begin{DoxyCompactList}\small\item\em Perform the forward pass of the data in real batch mode. \end{DoxyCompactList}\item {\footnotesize template$<$typename Predictors\+Type , typename Responses\+Type $>$ }\\void \textbf{ Forward} (const Predictors\+Type \&inputs, Responses\+Type \&results, const size\+\_\+t begin, const size\+\_\+t end) \begin{DoxyCompactList}\small\item\em Perform a partial forward pass of the data. \end{DoxyCompactList}\item void \textbf{ Gradient} (const arma\+::mat \¶meters, const size\+\_\+t begin, arma\+::mat \&gradient, const size\+\_\+t batch\+Size) \begin{DoxyCompactList}\small\item\em Evaluate the gradient of the feedforward network with the given parameters, and with respect to only a number of points in the dataset. \end{DoxyCompactList}\item const std\+::vector$<$ \textbf{ Layer\+Types}$<$ Custom\+Layers... $>$ $>$ \& \textbf{ Model} () const \begin{DoxyCompactList}\small\item\em Get the network model. \end{DoxyCompactList}\item std\+::vector$<$ \textbf{ Layer\+Types}$<$ Custom\+Layers... $>$ $>$ \& \textbf{ Model} () \begin{DoxyCompactList}\small\item\em Modify the network model. \end{DoxyCompactList}\item size\+\_\+t \textbf{ Num\+Functions} () const \begin{DoxyCompactList}\small\item\em Return the number of separable functions (the number of predictor points). \end{DoxyCompactList}\item \textbf{ F\+FN} \& \textbf{ operator=} (\textbf{ F\+FN}) \begin{DoxyCompactList}\small\item\em Copy/move assignment operator. \end{DoxyCompactList}\item const arma\+::mat \& \textbf{ Parameters} () const \begin{DoxyCompactList}\small\item\em Return the initial point for the optimization. \end{DoxyCompactList}\item arma\+::mat \& \textbf{ Parameters} () \begin{DoxyCompactList}\small\item\em Modify the initial point for the optimization. \end{DoxyCompactList}\item void \textbf{ Predict} (arma\+::mat predictors, arma\+::mat \&results) \begin{DoxyCompactList}\small\item\em Predict the responses to a given set of predictors. \end{DoxyCompactList}\item const arma\+::mat \& \textbf{ Predictors} () const \begin{DoxyCompactList}\small\item\em Get the matrix of data points (predictors). \end{DoxyCompactList}\item arma\+::mat \& \textbf{ Predictors} () \begin{DoxyCompactList}\small\item\em Modify the matrix of data points (predictors). \end{DoxyCompactList}\item void \textbf{ Reset\+Parameters} () \begin{DoxyCompactList}\small\item\em Reset the module infomration (weights/parameters). \end{DoxyCompactList}\item const arma\+::mat \& \textbf{ Responses} () const \begin{DoxyCompactList}\small\item\em Get the matrix of responses to the input data points. \end{DoxyCompactList}\item arma\+::mat \& \textbf{ Responses} () \begin{DoxyCompactList}\small\item\em Modify the matrix of responses to the input data points. \end{DoxyCompactList}\item {\footnotesize template$<$typename Archive $>$ }\\void \textbf{ serialize} (Archive \&ar, const unsigned int) \begin{DoxyCompactList}\small\item\em Serialize the model. \end{DoxyCompactList}\item void \textbf{ Shuffle} () \begin{DoxyCompactList}\small\item\em Shuffle the order of function visitation. \end{DoxyCompactList}\item {\footnotesize template$<$typename Optimizer\+Type , typename... Callback\+Types$>$ }\\double \textbf{ Train} (arma\+::mat predictors, arma\+::mat responses, Optimizer\+Type \&optimizer, Callback\+Types \&\&... callbacks) \begin{DoxyCompactList}\small\item\em Train the feedforward network on the given input data using the given optimizer. \end{DoxyCompactList}\item {\footnotesize template$<$typename Optimizer\+Type = ens\+::\+R\+M\+S\+Prop, typename... Callback\+Types$>$ }\\double \textbf{ Train} (arma\+::mat predictors, arma\+::mat responses, Callback\+Types \&\&... callbacks) \begin{DoxyCompactList}\small\item\em Train the feedforward network on the given input data. \end{DoxyCompactList}\item {\footnotesize template$<$typename Optimizer\+Type $>$ }\\std\+::enable\+\_\+if$<$ Has\+Max\+Iterations$<$ Optimizer\+Type, size\+\_\+t \&(Optimizer\+Type\+::$\ast$)()$>$\+::value, void $>$\+::type \textbf{ Warn\+Message\+Max\+Iterations} (Optimizer\+Type \&optimizer, size\+\_\+t samples) const \begin{DoxyCompactList}\small\item\em Check if the optimizer has Max\+Iterations() parameter, if it does then check if it\textquotesingle{}s value is less than the number of datapoints in the dataset. \end{DoxyCompactList}\item {\footnotesize template$<$typename Optimizer\+Type $>$ }\\std\+::enable\+\_\+if$<$ !Has\+Max\+Iterations$<$ Optimizer\+Type, size\+\_\+t \&(Optimizer\+Type\+::$\ast$)()$>$\+::value, void $>$\+::type \textbf{ Warn\+Message\+Max\+Iterations} (Optimizer\+Type \&optimizer, size\+\_\+t samples) const \begin{DoxyCompactList}\small\item\em Check if the optimizer has Max\+Iterations() parameter, if it doesn\textquotesingle{}t then simply return from the function. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Output\+Layer\+Type = Negative\+Log\+Likelihood$<$$>$, typename Initialization\+Rule\+Type = Random\+Initialization, typename... Custom\+Layers$>$\newline class mlpack\+::ann\+::\+F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$} Implementation of a standard feed forward network. \begin{DoxyTemplParams}{Template Parameters} {\em Output\+Layer\+Type} & The output layer type used to evaluate the network. \\ \hline {\em Initialization\+Rule\+Type} & Rule used to initialize the weight matrix. \\ \hline {\em Custom\+Layers} & Any set of custom layers that could be a part of the feed forward network. \\ \hline \end{DoxyTemplParams} Definition at line 52 of file ffn.\+hpp. \subsection{Member Typedef Documentation} \mbox{\label{classmlpack_1_1ann_1_1FFN_aa628987cefe24b56f3c1551d0588a329}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Network\+Type@{Network\+Type}} \index{Network\+Type@{Network\+Type}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Network\+Type} {\footnotesize\ttfamily using \textbf{ Network\+Type} = \textbf{ F\+FN}$<$Output\+Layer\+Type, Initialization\+Rule\+Type$>$} Convenience typedef for the internal model construction. Definition at line 56 of file ffn.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1FFN_a8a1597bba65304f53ae1cecd73b395a6}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!F\+FN@{F\+FN}} \index{F\+FN@{F\+FN}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{F\+F\+N()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily \textbf{ F\+FN} (\begin{DoxyParamCaption}\item[{Output\+Layer\+Type}]{output\+Layer = {\ttfamily OutputLayerType()}, }\item[{Initialization\+Rule\+Type}]{initialize\+Rule = {\ttfamily InitializationRuleType()} }\end{DoxyParamCaption})} Create the \doxyref{F\+FN}{p.}{classmlpack_1_1ann_1_1FFN} object. Optionally, specify which initialize rule and performance function should be used. If you want to pass in a parameter and discard the original parameter object, be sure to use std\+::move to avoid unnecessary copy. \begin{DoxyParams}{Parameters} {\em output\+Layer} & Output layer used to evaluate the network. \\ \hline {\em initialize\+Rule} & Optional instantiated Initialization\+Rule object for initializing the network parameter. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_a747c838260bf79c9b08e310660792800}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!F\+FN@{F\+FN}} \index{F\+FN@{F\+FN}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{F\+F\+N()\hspace{0.1cm}{\footnotesize\ttfamily [2/3]}} {\footnotesize\ttfamily \textbf{ F\+FN} (\begin{DoxyParamCaption}\item[{const \textbf{ F\+FN}$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$ \&}]{ }\end{DoxyParamCaption})} Copy constructor. \mbox{\label{classmlpack_1_1ann_1_1FFN_a8aa14d013d2855c06df5d78b31a126ef}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!F\+FN@{F\+FN}} \index{F\+FN@{F\+FN}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{F\+F\+N()\hspace{0.1cm}{\footnotesize\ttfamily [3/3]}} {\footnotesize\ttfamily \textbf{ F\+FN} (\begin{DoxyParamCaption}\item[{\textbf{ F\+FN}$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$ \&\&}]{ }\end{DoxyParamCaption})} Move constructor. \mbox{\label{classmlpack_1_1ann_1_1FFN_a45450c5c89a5be407cbaa16523c1533d}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!````~F\+FN@{$\sim$\+F\+FN}} \index{````~F\+FN@{$\sim$\+F\+FN}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{$\sim$\+F\+F\+N()} {\footnotesize\ttfamily $\sim$\textbf{ F\+FN} (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Destructor to release allocated memory. \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1FFN_a8b5234495846c00f6b2c8296ca6bc718}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Add@{Add}} \index{Add@{Add}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Add()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily void \textbf{ Add} (\begin{DoxyParamCaption}\item[{Args...}]{args }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Definition at line 292 of file ffn.\+hpp. Referenced by Simple\+D\+Q\+N$<$ Network\+Type $>$\+::\+Simple\+D\+Q\+N(). \mbox{\label{classmlpack_1_1ann_1_1FFN_a503a807740e6c729be9efc89520db728}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Add@{Add}} \index{Add@{Add}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Add()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily void \textbf{ Add} (\begin{DoxyParamCaption}\item[{\textbf{ Layer\+Types}$<$ Custom\+Layers... $>$}]{layer }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Definition at line 299 of file ffn.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1FFN_aa470bcf2d35a2b8489ee1be4d0485bf7}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Backward()} {\footnotesize\ttfamily double Backward (\begin{DoxyParamCaption}\item[{const Predictors\+Type \&}]{inputs, }\item[{const Targets\+Type \&}]{targets, }\item[{Gradients\+Type \&}]{gradients }\end{DoxyParamCaption})} Perform the backward pass of the data in real batch mode. Forward and Backward should be used as a pair, and they are designed mainly for advanced users. User should try to use Predict and Train unless those two functions can\textquotesingle{}t satisfy some special requirements. \begin{DoxyParams}{Parameters} {\em targets} & The training target. \\ \hline {\em gradients} & Computed gradients. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} Training error of the current pass. \end{DoxyReturn} Referenced by F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Predictors(). \mbox{\label{classmlpack_1_1ann_1_1FFN_a3eb237d1741e9c450dd695a84d9e8f50}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [1/4]}} {\footnotesize\ttfamily double Evaluate (\begin{DoxyParamCaption}\item[{const Predictors\+Type \&}]{predictors, }\item[{const Responses\+Type \&}]{responses }\end{DoxyParamCaption})} Evaluate the feedforward network with the given predictors and responses. This functions is usually used to monitor progress while training. \begin{DoxyParams}{Parameters} {\em predictors} & Input variables. \\ \hline {\em responses} & Target outputs for input variables. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_a1ca0efaedbc2e7e7542c89901cdcf2ee}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [2/4]}} {\footnotesize\ttfamily double Evaluate (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters }\end{DoxyParamCaption})} Evaluate the feedforward network with the given parameters. This function is usually called by the optimizer to train the model. \begin{DoxyParams}{Parameters} {\em parameters} & Matrix model parameters. \\ \hline {\em deterministic} & Whether or not to train or test the model. Note some layer act differently in training or testing mode. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_a3e02a8743fd14b2a902a2e090da2df47}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [3/4]}} {\footnotesize\ttfamily double Evaluate (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{begin, }\item[{const size\+\_\+t}]{batch\+Size, }\item[{const bool}]{deterministic }\end{DoxyParamCaption})} Evaluate the feedforward network with the given parameters, but using only a number of data points. This is useful for optimizers such as S\+GD, which require a separable objective function. \begin{DoxyParams}{Parameters} {\em parameters} & Matrix model parameters. \\ \hline {\em begin} & Index of the starting point to use for objective function evaluation. \\ \hline {\em batch\+Size} & Number of points to be passed at a time to use for objective function evaluation. \\ \hline {\em deterministic} & Whether or not to train or test the model. Note some layer act differently in training or testing mode. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_a8a04cfd951b52327d7f2e148c68f365d}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Evaluate@{Evaluate}} \index{Evaluate@{Evaluate}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Evaluate()\hspace{0.1cm}{\footnotesize\ttfamily [4/4]}} {\footnotesize\ttfamily double Evaluate (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{begin, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Evaluate the feedforward network with the given parameters, but using only a number of data points. This is useful for optimizers such as S\+GD, which require a separable objective function. This just calls the overload of \doxyref{Evaluate()}{p.}{classmlpack_1_1ann_1_1FFN_a3eb237d1741e9c450dd695a84d9e8f50} with deterministic = true. \begin{DoxyParams}{Parameters} {\em parameters} & Matrix model parameters. \\ \hline {\em begin} & Index of the starting point to use for objective function evaluation. \\ \hline {\em batch\+Size} & Number of points to be passed at a time to use for objective function evaluation. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_a8e99a4877511dea38ab32a2de7afe125}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}} \index{Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Evaluate\+With\+Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double Evaluate\+With\+Gradient (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{Grad\+Type \&}]{gradient }\end{DoxyParamCaption})} Evaluate the feedforward network with the given parameters. This function is usually called by the optimizer to train the model. This just calls the overload of \doxyref{Evaluate\+With\+Gradient()}{p.}{classmlpack_1_1ann_1_1FFN_a8e99a4877511dea38ab32a2de7afe125} with batch\+Size = 1. \begin{DoxyParams}{Parameters} {\em parameters} & Matrix model parameters. \\ \hline {\em gradient} & Matrix to output gradient into. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_a3e01e9e3fe4f5bd8cfc78521567a0f5a}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}} \index{Evaluate\+With\+Gradient@{Evaluate\+With\+Gradient}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Evaluate\+With\+Gradient()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily double Evaluate\+With\+Gradient (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{begin, }\item[{Grad\+Type \&}]{gradient, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Evaluate the feedforward network with the given parameters, but using only a number of data points. This is useful for optimizers such as S\+GD, which require a separable objective function. \begin{DoxyParams}{Parameters} {\em parameters} & Matrix model parameters. \\ \hline {\em begin} & Index of the starting point to use for objective function evaluation. \\ \hline {\em gradient} & Matrix to output gradient into. \\ \hline {\em batch\+Size} & Number of points to be passed at a time to use for objective function evaluation. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_a2f9b7c651427add841fa6ce2fa3f68e1}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Forward()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily void Forward (\begin{DoxyParamCaption}\item[{const Predictors\+Type \&}]{inputs, }\item[{Responses\+Type \&}]{results }\end{DoxyParamCaption})} Perform the forward pass of the data in real batch mode. Forward and Backward should be used as a pair, and they are designed mainly for advanced users. User should try to use Predict and Train unless those two functions can\textquotesingle{}t satisfy some special requirements. \begin{DoxyParams}{Parameters} {\em inputs} & The input data. \\ \hline {\em results} & The predicted results. \\ \hline \end{DoxyParams} Referenced by F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Predictors(). \mbox{\label{classmlpack_1_1ann_1_1FFN_a5f146cf28feb9ad8cb4891114536d97d}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Forward()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily void Forward (\begin{DoxyParamCaption}\item[{const Predictors\+Type \&}]{inputs, }\item[{Responses\+Type \&}]{results, }\item[{const size\+\_\+t}]{begin, }\item[{const size\+\_\+t}]{end }\end{DoxyParamCaption})} Perform a partial forward pass of the data. This function is meant for the cases when users require a forward pass only through certain layers and not the entire network. \begin{DoxyParams}{Parameters} {\em inputs} & The input data for the specified first layer. \\ \hline {\em results} & The predicted results from the specified last layer. \\ \hline {\em begin} & The index of the first layer. \\ \hline {\em end} & The index of the last layer. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_aca73798d93d56b280185c01502d8bd13}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Gradient@{Gradient}} \index{Gradient@{Gradient}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Gradient()} {\footnotesize\ttfamily void Gradient (\begin{DoxyParamCaption}\item[{const arma\+::mat \&}]{parameters, }\item[{const size\+\_\+t}]{begin, }\item[{arma\+::mat \&}]{gradient, }\item[{const size\+\_\+t}]{batch\+Size }\end{DoxyParamCaption})} Evaluate the gradient of the feedforward network with the given parameters, and with respect to only a number of points in the dataset. This is useful for optimizers such as S\+GD, which require a separable objective function. \begin{DoxyParams}{Parameters} {\em parameters} & Matrix of the model parameters to be optimized. \\ \hline {\em begin} & Index of the starting point to use for objective function gradient evaluation. \\ \hline {\em gradient} & Matrix to output gradient into. \\ \hline {\em batch\+Size} & Number of points to be processed as a batch for objective function gradient evaluation. \\ \hline \end{DoxyParams} Referenced by F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Predictors(). \mbox{\label{classmlpack_1_1ann_1_1FFN_a13efc1008a3923a70c7785e9470853a7}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Model@{Model}} \index{Model@{Model}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Model()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const std\+::vector$<$\textbf{ Layer\+Types}$<$Custom\+Layers...$>$ $>$\& Model (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the network model. Definition at line 302 of file ffn.\+hpp. Referenced by F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Predictors(). \mbox{\label{classmlpack_1_1ann_1_1FFN_a4cb1e93bff99ccf1f8f974065a3b13c3}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Model@{Model}} \index{Model@{Model}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Model()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily std\+::vector$<$\textbf{ Layer\+Types}$<$Custom\+Layers...$>$ $>$\& Model (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the network model. Be careful! If you change the structure of the network or parameters for layers, its state may become invalid, so be sure to call \doxyref{Reset\+Parameters()}{p.}{classmlpack_1_1ann_1_1FFN_a7178038c3cb8d247eadb94cd2058c432} afterwards. Definition at line 309 of file ffn.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1FFN_a1fa76af34a6e3ea927b307f0c318ee4b}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Num\+Functions@{Num\+Functions}} \index{Num\+Functions@{Num\+Functions}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Num\+Functions()} {\footnotesize\ttfamily size\+\_\+t Num\+Functions (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Return the number of separable functions (the number of predictor points). Definition at line 312 of file ffn.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1FFN_ad3218e6a988d7203fd6a0ced3e457057}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!operator=@{operator=}} \index{operator=@{operator=}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{operator=()} {\footnotesize\ttfamily \textbf{ F\+FN}\& operator= (\begin{DoxyParamCaption}\item[{\textbf{ F\+FN}$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$}]{ }\end{DoxyParamCaption})} Copy/move assignment operator. \mbox{\label{classmlpack_1_1ann_1_1FFN_aa68d74dc1e86e4352e00a3cab83a0e4a}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Parameters()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const arma\+::mat\& Parameters (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Return the initial point for the optimization. Definition at line 315 of file ffn.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1FFN_a043f0ccd62e6711a18e0d81047be9a0a}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Parameters@{Parameters}} \index{Parameters@{Parameters}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Parameters()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily arma\+::mat\& Parameters (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the initial point for the optimization. Definition at line 317 of file ffn.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1FFN_abf82c92c2116f34fb36118155da42a4e}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Predict@{Predict}} \index{Predict@{Predict}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Predict()} {\footnotesize\ttfamily void Predict (\begin{DoxyParamCaption}\item[{arma\+::mat}]{predictors, }\item[{arma\+::mat \&}]{results }\end{DoxyParamCaption})} Predict the responses to a given set of predictors. The responses will reflect the output of the given output layer as returned by the output layer function. If you want to pass in a parameter and discard the original parameter object, be sure to use std\+::move to avoid unnecessary copy. \begin{DoxyParams}{Parameters} {\em predictors} & Input predictors. \\ \hline {\em results} & Matrix to put output predictions of responses into. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_af63d9ce84ba796336c0abce63ff9be1c}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Predictors@{Predictors}} \index{Predictors@{Predictors}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Predictors()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const arma\+::mat\& Predictors (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the matrix of data points (predictors). Definition at line 325 of file ffn.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1FFN_a5b2b9103f156a387b74164f143e63ce7}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Predictors@{Predictors}} \index{Predictors@{Predictors}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Predictors()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily arma\+::mat\& Predictors (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the matrix of data points (predictors). Definition at line 327 of file ffn.\+hpp. References F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Backward(), F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Forward(), F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Gradient(), F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Model(), F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Reset\+Parameters(), and F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1FFN_a7178038c3cb8d247eadb94cd2058c432}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Reset\+Parameters@{Reset\+Parameters}} \index{Reset\+Parameters@{Reset\+Parameters}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Reset\+Parameters()} {\footnotesize\ttfamily void Reset\+Parameters (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Reset the module infomration (weights/parameters). Referenced by F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Predictors(). \mbox{\label{classmlpack_1_1ann_1_1FFN_a5702d7dbe418472e341da9c8d8ff0e01}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Responses@{Responses}} \index{Responses@{Responses}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Responses()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const arma\+::mat\& Responses (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the matrix of responses to the input data points. Definition at line 320 of file ffn.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1FFN_a94a56f6f545988833a4ae9906f8aa197}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Responses@{Responses}} \index{Responses@{Responses}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Responses()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily arma\+::mat\& Responses (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the matrix of responses to the input data points. Definition at line 322 of file ffn.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1FFN_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the model. Referenced by F\+F\+N$<$ Output\+Layer\+Type, Initialization\+Rule\+Type, Custom\+Layers $>$\+::\+Predictors(). \mbox{\label{classmlpack_1_1ann_1_1FFN_a2697cc8b37d7bca7c055228382a9b208}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Shuffle@{Shuffle}} \index{Shuffle@{Shuffle}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Shuffle()} {\footnotesize\ttfamily void Shuffle (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})} Shuffle the order of function visitation. This may be called by the optimizer. \mbox{\label{classmlpack_1_1ann_1_1FFN_adafbb7eca07a0b852cca46b154c5aab8}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Train@{Train}} \index{Train@{Train}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Train()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double Train (\begin{DoxyParamCaption}\item[{arma\+::mat}]{predictors, }\item[{arma\+::mat}]{responses, }\item[{Optimizer\+Type \&}]{optimizer, }\item[{Callback\+Types \&\&...}]{callbacks }\end{DoxyParamCaption})} Train the feedforward network on the given input data using the given optimizer. This will use the existing model parameters as a starting point for the optimization. If this is not what you want, then you should access the parameters vector directly with \doxyref{Parameters()}{p.}{classmlpack_1_1ann_1_1FFN_a043f0ccd62e6711a18e0d81047be9a0a} and modify it as desired. If you want to pass in a parameter and discard the original parameter object, be sure to use std\+::move to avoid unnecessary copy. \begin{DoxyTemplParams}{Template Parameters} {\em Optimizer\+Type} & Type of optimizer to use to train the model. \\ \hline {\em Callback\+Types} & Types of Callback Functions. \\ \hline \end{DoxyTemplParams} \begin{DoxyParams}{Parameters} {\em predictors} & Input training variables. \\ \hline {\em responses} & Outputs results from input training variables. \\ \hline {\em optimizer} & Instantiated optimizer used to train the model. \\ \hline {\em callbacks} & Callback function for ensmallen optimizer {\ttfamily Optimizer\+Type}. See {\tt https\+://www.\+ensmallen.\+org/docs.\+html\#callback-\/documentation}. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} The final objective of the trained model (NaN or Inf on error). \end{DoxyReturn} \mbox{\label{classmlpack_1_1ann_1_1FFN_a4b7575e89c27b66658f50510ef2e639b}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Train@{Train}} \index{Train@{Train}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Train()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily double Train (\begin{DoxyParamCaption}\item[{arma\+::mat}]{predictors, }\item[{arma\+::mat}]{responses, }\item[{Callback\+Types \&\&...}]{callbacks }\end{DoxyParamCaption})} Train the feedforward network on the given input data. By default, the R\+M\+S\+Prop optimization algorithm is used, but others can be specified (such as ens\+::\+S\+GD). This will use the existing model parameters as a starting point for the optimization. If this is not what you want, then you should access the parameters vector directly with \doxyref{Parameters()}{p.}{classmlpack_1_1ann_1_1FFN_a043f0ccd62e6711a18e0d81047be9a0a} and modify it as desired. If you want to pass in a parameter and discard the original parameter object, be sure to use std\+::move to avoid unnecessary copy. \begin{DoxyTemplParams}{Template Parameters} {\em Optimizer\+Type} & Type of optimizer to use to train the model. \\ \hline \end{DoxyTemplParams} \begin{DoxyParams}{Parameters} {\em predictors} & Input training variables. \\ \hline \end{DoxyParams} \begin{DoxyTemplParams}{Template Parameters} {\em Callback\+Types} & Types of Callback Functions. \\ \hline \end{DoxyTemplParams} \begin{DoxyParams}{Parameters} {\em responses} & Outputs results from input training variables. \\ \hline {\em callbacks} & Callback function for ensmallen optimizer {\ttfamily Optimizer\+Type}. See {\tt https\+://www.\+ensmallen.\+org/docs.\+html\#callback-\/documentation}. \\ \hline \end{DoxyParams} \begin{DoxyReturn}{Returns} The final objective of the trained model (NaN or Inf on error). \end{DoxyReturn} \mbox{\label{classmlpack_1_1ann_1_1FFN_a5a15e2d0145f9a32c5b439d9d1949908}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Warn\+Message\+Max\+Iterations@{Warn\+Message\+Max\+Iterations}} \index{Warn\+Message\+Max\+Iterations@{Warn\+Message\+Max\+Iterations}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Warn\+Message\+Max\+Iterations()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$ Has\+Max\+Iterations$<$Optimizer\+Type, size\+\_\+t\&(Optimizer\+Type\+::$\ast$)()$>$\+::value, void$>$\+::type Warn\+Message\+Max\+Iterations (\begin{DoxyParamCaption}\item[{Optimizer\+Type \&}]{optimizer, }\item[{size\+\_\+t}]{samples }\end{DoxyParamCaption}) const} Check if the optimizer has Max\+Iterations() parameter, if it does then check if it\textquotesingle{}s value is less than the number of datapoints in the dataset. \begin{DoxyTemplParams}{Template Parameters} {\em Optimizer\+Type} & Type of optimizer to use to train the model. \\ \hline \end{DoxyTemplParams} \begin{DoxyParams}{Parameters} {\em optimizer} & optimizer used in the training process. \\ \hline {\em samples} & Number of datapoints in the dataset. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1FFN_a02d59875a99c37ae210353881619d1af}} \index{mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}!Warn\+Message\+Max\+Iterations@{Warn\+Message\+Max\+Iterations}} \index{Warn\+Message\+Max\+Iterations@{Warn\+Message\+Max\+Iterations}!mlpack\+::ann\+::\+F\+FN@{mlpack\+::ann\+::\+F\+FN}} \subsubsection{Warn\+Message\+Max\+Iterations()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily std\+::enable\+\_\+if$<$ !Has\+Max\+Iterations$<$Optimizer\+Type, size\+\_\+t\&(Optimizer\+Type\+::$\ast$)()$>$\+::value, void$>$\+::type Warn\+Message\+Max\+Iterations (\begin{DoxyParamCaption}\item[{Optimizer\+Type \&}]{optimizer, }\item[{size\+\_\+t}]{samples }\end{DoxyParamCaption}) const} Check if the optimizer has Max\+Iterations() parameter, if it doesn\textquotesingle{}t then simply return from the function. \begin{DoxyTemplParams}{Template Parameters} {\em Optimizer\+Type} & Type of optimizer to use to train the model. \\ \hline \end{DoxyTemplParams} \begin{DoxyParams}{Parameters} {\em optimizer} & optimizer used in the training process. \\ \hline {\em samples} & Number of datapoints in the dataset. \\ \hline \end{DoxyParams} The documentation for this class was generated from the following file\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/3.\+3.\+1/src/mlpack/methods/ann/\textbf{ ffn.\+hpp}\end{DoxyCompactItemize}