\section{Perceptron$<$ Learn\+Policy, Weight\+Initialization\+Policy, Mat\+Type $>$ Class Template Reference} \label{classmlpack_1_1perceptron_1_1Perceptron}\index{Perceptron$<$ Learn\+Policy, Weight\+Initialization\+Policy, Mat\+Type $>$@{Perceptron$<$ Learn\+Policy, Weight\+Initialization\+Policy, Mat\+Type $>$}} This class implements a simple perceptron (i.\+e., a single layer neural network). \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Perceptron} (const size\+\_\+t num\+Classes=0, const size\+\_\+t dimensionality=0, const size\+\_\+t max\+Iterations=1000) \begin{DoxyCompactList}\small\item\em Constructor\+: create the perceptron with the given number of classes and initialize the weight matrix, but do not perform any training. \end{DoxyCompactList}\item \textbf{ Perceptron} (const Mat\+Type \&data, const arma\+::\+Row$<$ size\+\_\+t $>$ \&labels, const size\+\_\+t num\+Classes, const size\+\_\+t max\+Iterations=1000) \begin{DoxyCompactList}\small\item\em Constructor\+: constructs the perceptron by building the weights matrix, which is later used in classification. \end{DoxyCompactList}\item \textbf{ Perceptron} (const \textbf{ Perceptron} \&other, const Mat\+Type \&data, const arma\+::\+Row$<$ size\+\_\+t $>$ \&labels, const size\+\_\+t num\+Classes, const arma\+::rowvec \&instance\+Weights) \begin{DoxyCompactList}\small\item\em Alternate constructor which copies parameters from an already initiated perceptron. \end{DoxyCompactList}\item const arma\+::vec \& \textbf{ Biases} () const \begin{DoxyCompactList}\small\item\em Get the biases. \end{DoxyCompactList}\item arma\+::vec \& \textbf{ Biases} () \begin{DoxyCompactList}\small\item\em Modify the biases. You had better know what you are doing! \end{DoxyCompactList}\item void \textbf{ Classify} (const Mat\+Type \&test, arma\+::\+Row$<$ size\+\_\+t $>$ \&predicted\+Labels) \begin{DoxyCompactList}\small\item\em Classification function. \end{DoxyCompactList}\item size\+\_\+t \textbf{ Max\+Iterations} () const \begin{DoxyCompactList}\small\item\em Get the maximum number of iterations. \end{DoxyCompactList}\item size\+\_\+t \& \textbf{ Max\+Iterations} () \begin{DoxyCompactList}\small\item\em Modify the maximum number of iterations. \end{DoxyCompactList}\item size\+\_\+t \textbf{ Num\+Classes} () const \begin{DoxyCompactList}\small\item\em Get the number of classes this perceptron has been trained for. \end{DoxyCompactList}\item {\footnotesize template$<$typename Archive $>$ }\\void \textbf{ serialize} (Archive \&ar, const unsigned int) \begin{DoxyCompactList}\small\item\em Serialize the perceptron. \end{DoxyCompactList}\item void \textbf{ Train} (const Mat\+Type \&data, const arma\+::\+Row$<$ size\+\_\+t $>$ \&labels, const size\+\_\+t num\+Classes, const arma\+::rowvec \&instance\+Weights=arma\+::rowvec()) \begin{DoxyCompactList}\small\item\em Train the perceptron on the given data for up to the maximum number of iterations (specified in the constructor or through \doxyref{Max\+Iterations()}{p.}{classmlpack_1_1perceptron_1_1Perceptron_acda675ab4ab86b95c92bc33bc391a61b}). \end{DoxyCompactList}\item const arma\+::mat \& \textbf{ Weights} () const \begin{DoxyCompactList}\small\item\em Get the weight matrix. \end{DoxyCompactList}\item arma\+::mat \& \textbf{ Weights} () \begin{DoxyCompactList}\small\item\em Modify the weight matrix. You had better know what you are doing! \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Learn\+Policy = Simple\+Weight\+Update, typename Weight\+Initialization\+Policy = Zero\+Initialization, typename Mat\+Type = arma\+::mat$>$\newline class mlpack\+::perceptron\+::\+Perceptron$<$ Learn\+Policy, Weight\+Initialization\+Policy, Mat\+Type $>$} This class implements a simple perceptron (i.\+e., a single layer neural network). It converges if the supplied training dataset is linearly separable. \begin{DoxyTemplParams}{Template Parameters} {\em Learn\+Policy} & Options of \doxyref{Simple\+Weight\+Update}{p.}{classmlpack_1_1perceptron_1_1SimpleWeightUpdate} and Gradient\+Descent. \\ \hline {\em Weight\+Initialization\+Policy} & Option of \doxyref{Zero\+Initialization}{p.}{classmlpack_1_1perceptron_1_1ZeroInitialization} and \doxyref{Random\+Initialization}{p.}{classmlpack_1_1perceptron_1_1RandomInitialization}. \\ \hline \end{DoxyTemplParams} Definition at line 36 of file perceptron.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_afb05a42d7d7f430b1243af7b45eff050}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Perceptron@{Perceptron}} \index{Perceptron@{Perceptron}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Perceptron()\hspace{0.1cm}{\footnotesize\ttfamily [1/3]}} {\footnotesize\ttfamily \textbf{ Perceptron} (\begin{DoxyParamCaption}\item[{const size\+\_\+t}]{num\+Classes = {\ttfamily 0}, }\item[{const size\+\_\+t}]{dimensionality = {\ttfamily 0}, }\item[{const size\+\_\+t}]{max\+Iterations = {\ttfamily 1000} }\end{DoxyParamCaption})} Constructor\+: create the perceptron with the given number of classes and initialize the weight matrix, but do not perform any training. (Call the \doxyref{Train()}{p.}{classmlpack_1_1perceptron_1_1Perceptron_a949c54b4d4873f2ad0aaef9ca9572a7a} function to perform training.) \begin{DoxyParams}{Parameters} {\em num\+Classes} & Number of classes in the dataset. \\ \hline {\em dimensionality} & Dimensionality of the dataset. \\ \hline {\em max\+Iterations} & Maximum number of iterations for the perceptron learning algorithm. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_a9c07dd0448fb853fa3a27a3c6e45a7b0}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Perceptron@{Perceptron}} \index{Perceptron@{Perceptron}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Perceptron()\hspace{0.1cm}{\footnotesize\ttfamily [2/3]}} {\footnotesize\ttfamily \textbf{ Perceptron} (\begin{DoxyParamCaption}\item[{const Mat\+Type \&}]{data, }\item[{const arma\+::\+Row$<$ size\+\_\+t $>$ \&}]{labels, }\item[{const size\+\_\+t}]{num\+Classes, }\item[{const size\+\_\+t}]{max\+Iterations = {\ttfamily 1000} }\end{DoxyParamCaption})} Constructor\+: constructs the perceptron by building the weights matrix, which is later used in classification. The number of classes should be specified separately, and the labels vector should contain values in the range [0, num\+Classes -\/ 1]. The \doxyref{data\+::\+Normalize\+Labels()}{p.}{namespacemlpack_1_1data_a664b3fa5243889e2aed47ee750f840ed} function can be used if the labels vector does not contain values in the required range. \begin{DoxyParams}{Parameters} {\em data} & Input, training data. \\ \hline {\em labels} & Labels of dataset. \\ \hline {\em num\+Classes} & Number of classes in the dataset. \\ \hline {\em max\+Iterations} & Maximum number of iterations for the perceptron learning algorithm. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_af848be7d79b355aabd033029e9dda539}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Perceptron@{Perceptron}} \index{Perceptron@{Perceptron}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Perceptron()\hspace{0.1cm}{\footnotesize\ttfamily [3/3]}} {\footnotesize\ttfamily \textbf{ Perceptron} (\begin{DoxyParamCaption}\item[{const \textbf{ Perceptron}$<$ Learn\+Policy, Weight\+Initialization\+Policy, Mat\+Type $>$ \&}]{other, }\item[{const Mat\+Type \&}]{data, }\item[{const arma\+::\+Row$<$ size\+\_\+t $>$ \&}]{labels, }\item[{const size\+\_\+t}]{num\+Classes, }\item[{const arma\+::rowvec \&}]{instance\+Weights }\end{DoxyParamCaption})} Alternate constructor which copies parameters from an already initiated perceptron. \begin{DoxyParams}{Parameters} {\em other} & The other initiated \doxyref{Perceptron}{p.}{classmlpack_1_1perceptron_1_1Perceptron} object from which we copy the values from. \\ \hline {\em data} & The data on which to train this \doxyref{Perceptron}{p.}{classmlpack_1_1perceptron_1_1Perceptron} object on. \\ \hline {\em labels} & The labels of data. \\ \hline {\em num\+Classes} & Number of classes in the data. \\ \hline {\em instance\+Weights} & Weight vector to use while training. For boosting purposes. \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_ab0de0c2cd97b7ec0c19098b50cb769ee}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Biases@{Biases}} \index{Biases@{Biases}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Biases()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const arma\+::vec\& Biases (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the biases. Definition at line 139 of file perceptron.\+hpp. \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_ab6edaa6e34b69382b776ad80a70508a7}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Biases@{Biases}} \index{Biases@{Biases}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Biases()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily arma\+::vec\& Biases (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the biases. You had better know what you are doing! Definition at line 141 of file perceptron.\+hpp. \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_a407f9c281dab80fffd49251d3907838d}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Classify@{Classify}} \index{Classify@{Classify}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Classify()} {\footnotesize\ttfamily void Classify (\begin{DoxyParamCaption}\item[{const Mat\+Type \&}]{test, }\item[{arma\+::\+Row$<$ size\+\_\+t $>$ \&}]{predicted\+Labels }\end{DoxyParamCaption})} Classification function. After training, use the weights matrix to classify test, and put the predicted classes in predicted\+Labels. \begin{DoxyParams}{Parameters} {\em test} & Testing data or data to classify. \\ \hline {\em predicted\+Labels} & Vector to store the predicted classes after classifying test. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_a420770944a5b0c7a852c4ec372c4a2d1}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Max\+Iterations@{Max\+Iterations}} \index{Max\+Iterations@{Max\+Iterations}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Max\+Iterations()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily size\+\_\+t Max\+Iterations (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the maximum number of iterations. Definition at line 126 of file perceptron.\+hpp. \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_acda675ab4ab86b95c92bc33bc391a61b}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Max\+Iterations@{Max\+Iterations}} \index{Max\+Iterations@{Max\+Iterations}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Max\+Iterations()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily size\+\_\+t\& Max\+Iterations (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the maximum number of iterations. Definition at line 128 of file perceptron.\+hpp. \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_a088ebfdf3c7a9e7eea81716d0c55b5a3}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Num\+Classes@{Num\+Classes}} \index{Num\+Classes@{Num\+Classes}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Num\+Classes()} {\footnotesize\ttfamily size\+\_\+t Num\+Classes (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the number of classes this perceptron has been trained for. Definition at line 131 of file perceptron.\+hpp. \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the perceptron. \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_a949c54b4d4873f2ad0aaef9ca9572a7a}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Train@{Train}} \index{Train@{Train}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Train()} {\footnotesize\ttfamily void Train (\begin{DoxyParamCaption}\item[{const Mat\+Type \&}]{data, }\item[{const arma\+::\+Row$<$ size\+\_\+t $>$ \&}]{labels, }\item[{const size\+\_\+t}]{num\+Classes, }\item[{const arma\+::rowvec \&}]{instance\+Weights = {\ttfamily arma\+:\+:rowvec()} }\end{DoxyParamCaption})} Train the perceptron on the given data for up to the maximum number of iterations (specified in the constructor or through \doxyref{Max\+Iterations()}{p.}{classmlpack_1_1perceptron_1_1Perceptron_acda675ab4ab86b95c92bc33bc391a61b}). A single iteration corresponds to a single pass through the data, so if you want to pass through the dataset only once, set \doxyref{Max\+Iterations()}{p.}{classmlpack_1_1perceptron_1_1Perceptron_acda675ab4ab86b95c92bc33bc391a61b} to 1. This training does not reset the model weights, so you can call \doxyref{Train()}{p.}{classmlpack_1_1perceptron_1_1Perceptron_a949c54b4d4873f2ad0aaef9ca9572a7a} on multiple datasets sequentially. \begin{DoxyParams}{Parameters} {\em data} & Dataset on which training should be performed. \\ \hline {\em labels} & Labels of the dataset. \\ \hline {\em num\+Classes} & Number of classes in the data. \\ \hline {\em instance\+Weights} & Cost matrix. Stores the cost of mispredicting instances. This is useful for boosting. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_a3b90705a96848b77f63e61a664293a18}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Weights@{Weights}} \index{Weights@{Weights}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Weights()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily const arma\+::mat\& Weights (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the weight matrix. Definition at line 134 of file perceptron.\+hpp. \mbox{\label{classmlpack_1_1perceptron_1_1Perceptron_adb90a12c4180f2bb283f4a8820f26f9f}} \index{mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}!Weights@{Weights}} \index{Weights@{Weights}!mlpack\+::perceptron\+::\+Perceptron@{mlpack\+::perceptron\+::\+Perceptron}} \subsubsection{Weights()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily arma\+::mat\& Weights (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the weight matrix. You had better know what you are doing! Definition at line 136 of file perceptron.\+hpp. 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.\+2/src/mlpack/methods/perceptron/\textbf{ perceptron.\+hpp}\end{DoxyCompactItemize}