forked from TH_General/Template_Summary
Kernel Regression abgeschlossen
This commit is contained in:
parent
ecf712de93
commit
92ff396b36
41
Glossary.tex
41
Glossary.tex
@ -84,15 +84,16 @@
|
||||
%--------------------
|
||||
|
||||
%add new key
|
||||
\glsaddstoragekey{unit}{}{\glsentryunit}
|
||||
%\glsaddstoragekey{unit}{}{\glsentryunit}
|
||||
\glsnoexpandfields
|
||||
|
||||
\newcommand{\newnom}[5]{
|
||||
%\newcommand{\newnom}[5]{
|
||||
\newcommand{\newnom}[4]{
|
||||
\newglossaryentry{#1}{
|
||||
name={#2},
|
||||
symbol={#3},
|
||||
description={#4},
|
||||
unit={#5},
|
||||
%unit={#5},
|
||||
type=nomenclature,
|
||||
sort={#1}
|
||||
}
|
||||
@ -108,23 +109,23 @@
|
||||
%use nomenclature entry (use in equation)
|
||||
\newcommand{\nomeq}[1]{\glslink{#1}{\glsentrysymbol{#1}}}
|
||||
|
||||
\newnom{summed_squared_error}{\gls{SSE}}{\text{\glsxtrshort{SSE}}}{\glsxtrfull{SSE}}{}
|
||||
\newnom{mean_squared_error}{\gls{MSE}}{\text{\glsxtrshort{MSE}}}{\glsxtrfull{MSE}}{}
|
||||
\newnom{residual_sum_squares}{\gls{RSS}}{\text{\glsxtrshort{RSS}}}{\glsxtrfull{RSS}}{}
|
||||
\newnom{gaussian_noise}{Gausches Rauschen}{\epsilon}{zufällige (normalverteilte) Abweichung}{}
|
||||
\newnom{vector_valued_function}{vektorwertige Funktion}{\phi(\bm{x})}{vektorwertige Funktion der des Eingangsvektor $\bm{x}$}{}
|
||||
\newnom{regularization_factor}{Regularisierungsfaktor}{\lambda}{}{}
|
||||
\newnom{identity_matrix}{Identitätsmatrix}{\bm{I}}{$\begin{bmatrix} 1 & 0 & \cdots & 0 \\ 0 & 1 & \cdots & 0 \\ \vdots & \vdots & \ddots & \vdots\\ 0 & 0 & \cdots & 1 \end{bmatrix}$}{}
|
||||
\newnom{probability_mass_function}{Probability Mass Function}{p(x)}{Wahrscheinlichkeitsdichte-\slash\,Wahrscheinlichkeitsmassefunktion}{}
|
||||
\newnom{mean}{arithmetisches Mittel}{\mu}{}{}
|
||||
\newnom{mean-vector}{Mittelwerts-Vektor}{\bm{\mu}}{}{}
|
||||
\newnom{covariance}{Kovarianz-Matrix}{\bm{\Sigma}}{}{}
|
||||
\newnom{variance}{Varianz}{\sigma^2}{$\mathbb{E}_p[(X-\nomeq{mean})$]}{}
|
||||
\newnom{sigmoid}{Sigmoid Function}{\sigma}{}{}
|
||||
\newnom{learning_rate}{Learning Rate}{\eta}{}{}
|
||||
\newnom{kernel_matrix}{Kernel Matrix}{\bm{K}}{}{}
|
||||
\newnom{kernel_function}{Kernel Function}{k}{}{}
|
||||
\newnom{kernel_vector}{Kernel Vector}{\bm{k}}{}{}
|
||||
\newnom{summed_squared_error}{\gls{SSE}}{\text{\glsxtrshort{SSE}}}{\glsxtrfull{SSE}}
|
||||
\newnom{mean_squared_error}{\gls{MSE}}{\text{\glsxtrshort{MSE}}}{\glsxtrfull{MSE}}
|
||||
\newnom{residual_sum_squares}{\gls{RSS}}{\text{\glsxtrshort{RSS}}}{\glsxtrfull{RSS}}
|
||||
\newnom{gaussian_noise}{Gausches Rauschen}{\epsilon}{zufällige (normalverteilte) Abweichung}
|
||||
\newnom{vector_valued_function}{vektorwertige Funktion}{\bm\phi(\bm{x})}{vektorwertige Funktion der des Eingangsvektor $\bm{x}$}
|
||||
\newnom{regularization_factor}{Regularisierungsfaktor}{\lambda}{}
|
||||
\newnom{identity_matrix}{Identitätsmatrix}{\bm{I}}{$\begin{bmatrix} 1 & 0 & \cdots & 0 \\ 0 & 1 & \cdots & 0 \\ \vdots & \vdots & \ddots & \vdots\\ 0 & 0 & \cdots & 1 \end{bmatrix}$}
|
||||
\newnom{probability_mass_function}{Probability Mass Function}{p(x)}{Wahrscheinlichkeitsdichte-\slash\,Wahrscheinlichkeitsmassefunktion}
|
||||
\newnom{mean}{arithmetisches Mittel}{\mu}{}
|
||||
\newnom{mean-vector}{Mittelwerts-Vektor}{\bm{\mu}}{}
|
||||
\newnom{covariance}{Kovarianz-Matrix}{\bm{\Sigma}}{}
|
||||
\newnom{variance}{Varianz}{\sigma^2}{$\mathbb{E}_p[(X-\nomeq{mean})$]}
|
||||
\newnom{sigmoid}{Sigmoid Function}{\sigma}{}
|
||||
\newnom{learning_rate}{Learning Rate}{\eta}{}
|
||||
\newnom{kernel_matrix}{Kernel Matrix}{\bm{K}}{}
|
||||
\newnom{kernel_function}{Kernel Function}{k}{}
|
||||
\newnom{kernel_vector}{Kernel Vector}{\bm{k}}{}
|
||||
\shorthandoff{"}
|
||||
|
||||
\makeglossaries
|
||||
|
12
Preface.tex
12
Preface.tex
@ -25,17 +25,21 @@
|
||||
\renewcommand{\glsgroupskip}{}%avoids grouping the elements by alphabetical order
|
||||
\renewenvironment{theglossary}{% Change the table type --> 4 columns
|
||||
\renewcommand*{\arraystretch}{1.5}
|
||||
\begin{longtable}{>{\centering}p{.1\textwidth} >{\arraybackslash}p{.225\textwidth} p{.475\textwidth}>{\centering\arraybackslash}p{.1\textwidth}}}%
|
||||
%\begin{longtable}{>{\centering}p{.1\textwidth} >{\arraybackslash}p{.225\textwidth} p{.475\textwidth}>{\centering\arraybackslash}p{.1\textwidth}}}%
|
||||
\begin{longtable}{>{\centering}p{.1\textwidth} >{\arraybackslash}p{.225\textwidth} p{.575\textwidth}}}%
|
||||
{\end{longtable}}%
|
||||
%
|
||||
\renewcommand*{\glossaryheader}{% Change the table header
|
||||
\bfseries\large Symbol & \bfseries\large Bezeichnung & \large\bfseries Beschreibung & \large\bfseries Einheit\\
|
||||
%\bfseries\large Symbol & \bfseries\large Bezeichnung & \large\bfseries Beschreibung & \large\bfseries Einheit\\
|
||||
\bfseries\large Symbol & \bfseries\large Bezeichnung & \large\bfseries Beschreibung\\
|
||||
\hline\endhead}%
|
||||
\renewcommand*{\glossentry}[2]{% Change the displayed items
|
||||
\boldmath\ensuremath{\glossentrysymbol{##1}}
|
||||
%\boldmath\ensuremath{\glossentrysymbol{##1}}
|
||||
\ensuremath{\glossentrysymbol{##1}}
|
||||
& \glstarget{##1}{\hspace*{0pt}\glossentryname{##1}} %
|
||||
& \glossentrydesc{##1}
|
||||
& \glsentryunit{##1}\tabularnewline
|
||||
%& \glsentryunit{##1}
|
||||
\tabularnewline
|
||||
}%
|
||||
}
|
||||
\printglossary[type=nomenclature, nonumberlist, style=symbunitlong]
|
||||
|
@ -81,7 +81,7 @@ welchen Anteil die Klasse $k$ auf der linken Seite des Splits hat.
|
||||
\subsubsection{Classification Tree}%
|
||||
\label{ssub:Classification Tree}
|
||||
\includegraphics[width=.6\textwidth]{classification_tree.png}
|
||||
{\color{red} Herleitung Vorlesung 03 Seite 24-31}
|
||||
{\color{red} Herleitung Vorlesung 04 Seite 24-31}
|
||||
|
||||
\subsubsection{Regression Tree}%
|
||||
\label{ssub:Regression Tree}
|
||||
@ -96,7 +96,7 @@ Predict (log) prostate specific antigen from
|
||||
\end{itemize}
|
||||
}
|
||||
\vspace*{30mm}
|
||||
{\color{red} Herleitung Vorlesung 03 Seite 32-36}
|
||||
{\color{red} Herleitung Vorlesung 04 Seite 32-36}
|
||||
|
||||
\section{Random Forests}%
|
||||
\label{sec:Random Forests}
|
||||
|
@ -1,5 +1,52 @@
|
||||
\chapter{Kernel-Regression}%
|
||||
\label{cha:Kernel-Regression}
|
||||
Die Kernel Regression ist das Äquivalent der Linear \nameref{sub:Ridge Regression} (\cref{sub:Ridge Regression}),
|
||||
weshalb es auch oft als Kernel Ridge Regression bezeichnet wird.
|
||||
Die Linear Ridge Regression ist allerdings für den linearen Feature Space gedacht
|
||||
und lässt sich nicht direkt in einem Feature Space mit unendlicher Dimension anwenden.
|
||||
|
||||
WEITER AUF FOLIE 294
|
||||
Mithilfe eines mathematischen Tricks (aus dem Matrix Cookook) lässt sich die Lösung der Ridge Regression so umstellen,
|
||||
dass statt einer $d\times d$ Matrix lediglich eine $N\times N$ Matrix invertiert werden muss:
|
||||
\begin{equation}
|
||||
\bm w^* = \underbrace{(\bm\Phi^T\bm\Phi + \nomeq{regularization_factor}\nomeq{identity_matrix})^{-1}}_{\text{$d\times d$ matrix inversion}}\bm\Phi^T\bm y
|
||||
= \bm\Phi^T\underbrace{(\bm\Phi\bm\Phi^T + \nomeq{regularization_factor}\nomeq{identity_matrix})^{-1}}_{\text{$N\times N$ matrix inversion}}\bm y
|
||||
\end{equation}
|
||||
Nun erlaubt es die Verwendung einer \nomf{kernel_matrix} (\cref{cha:Kernel Basics}),
|
||||
die Gleichung weiter zu vereinfachen:
|
||||
\begin{equation}
|
||||
\bm w^* = \bm\Phi^T\underbrace{(\bm\Phi\bm\Phi^T + \nomeq{regularization_factor}\nomeq{identity_matrix})^{-1}}_{\text{$N\times N$ matrix inversion}}\bm y
|
||||
= \bm\Phi^T \underbrace{(\nomeq{kernel_matrix} + \nomeq{regularization_factor}\nomeq{identity_matrix})^{-1}\bm y}_{\bm \alpha}
|
||||
= \bm\Phi^T \bm\alpha
|
||||
\end{equation}
|
||||
Allerdings besteht weiterhin das Problem,
|
||||
dass $\bm w^* \mathbb{R}^d$ eine potentiell unendlich große Dimension hat
|
||||
und daher nicht dargestellt oder abgespeichert werden kann.
|
||||
Allerdings ermöglicht es und die Beschreibung mithilfe des Kernels,
|
||||
eine Funktion $f(\bm x)$,
|
||||
die $\bm w^*$ verwendet auszuwerten:
|
||||
\begin{equation}
|
||||
f(\bm x) = \nomeq{vector_valued_function}^T\bm w^*
|
||||
= \nomeq{vector_valued_function}^T\bm\Phi^T\bm\alpha
|
||||
= \nomeq{kernel_vector}(\bm x)^T\bm\alpha
|
||||
= \sum_i \alpha_i \nomeq{kernel_function}(\bm x_i,\bm x)
|
||||
\end{equation}
|
||||
Die Lösung der Kernel Ridge Regression wird daher gegeben durch:
|
||||
\begin{equation} \label{eq:kernel_ridge_regression_solution}
|
||||
f^*(\bm x) = \nomeq{kernel_vector}(\bm x)^T (\nomeq{kernel_matrix} + \nomeq{regularization_factor}\nomeq{identity_matrix})^{-1}\bm y
|
||||
\end{equation}
|
||||
|
||||
\section{Selecting the hyper-parameters}%
|
||||
\label{sub:Selecting the hyper-parameters}
|
||||
Die Auswahl der passenden Hyperparameter (z.B. \nomsym{variance} für den \nameref{sub:Gaussian Kernel}) ist ein Model Selection Problem (\cref{cha:Model Selection}).
|
||||
\begin{figure}[H]
|
||||
\centering
|
||||
\includegraphics[width=0.5\textwidth]{gaussian_kernel_model_selection.png}
|
||||
\caption{\nameref{cha:Model Selection} Problem für einen \nameref{sub:Gaussian Kernel}}
|
||||
\label{fig:gaussian_kernel_model_selection}
|
||||
\end{figure}
|
||||
|
||||
\section{Examples and comparison to \glsxtrshort{RBF} regression}%
|
||||
\label{sec:Examples and comparison to RBF regression}
|
||||
\begin{center}
|
||||
\includegraphics[width=.9\textwidth]{kernel_regression_comparison.pdf}
|
||||
\end{center}
|
||||
|
BIN
images/gaussian_kernel_model_selection.png
Normal file
BIN
images/gaussian_kernel_model_selection.png
Normal file
Binary file not shown.
After Width: | Height: | Size: 13 KiB |
BIN
images/kernel_regression_comparison.pdf
Normal file
BIN
images/kernel_regression_comparison.pdf
Normal file
Binary file not shown.
Loading…
x
Reference in New Issue
Block a user