case1/out/main.tex

\UseRawInputEncoding
%\documentclass[hyperref={pdfpagelabels=false}]{beamer}
\documentclass[hyperref={pdfpagelabels=false},aspectratio=169]{beamer}
% Die Hyperref Option hyperref={pdfpagelabels=false} verhindert die Warnung:
% Package hyperref Warning: Option `pdfpagelabels' is turned off
% (hyperref)                because \thepage is undefined. 
% Hyperref stopped early 
%

\usepackage{lmodern}
% Das Paket lmodern erspart die folgenden Warnungen:
% LaTeX Font Warning: Font shape `OT1/cmss/m/n' in size <4> not available
% (Font)              size <5> substituted on input line 22.
% LaTeX Font Warning: Size substitutions with differences
% (Font)              up to 1.0pt have occurred.
%

% Wenn \titel{\ldots} \author{\ldots} erst nach \begin{document} kommen,
% kommt folgende Warnung:
% Package hyperref Warning: Option `pdfauthor' has already been used,
% (hyperref) ... 
% Daher steht es hier vor \begin{document}

\title[AutoML4Rad]{Case Study - AutoML for Robust Anomaly Detection}   
\author{Simon Kluettermann} 
\date{\today} 


 \institute{ls9 tu Dortmund}


% Dadurch wird verhindert, dass die Navigationsleiste angezeigt wird.
\setbeamertemplate{navigation symbols}{}

% zusaetzlich ist das usepackage{beamerthemeshadow} eingebunden 
\usepackage{beamerthemeshadow}

\hypersetup{pdfstartview={Fit}} % fits the presentation to the window when first displayed

\usepackage{appendixnumberbeamer}
\usepackage{listings}


\usetheme{CambridgeUS}
\usepackage{ngerman}
\usecolortheme{dolphin}


%  \beamersetuncovermixins{\opaqueness<1>{25}}{\opaqueness<2$\Rightarrow${15}}
%  sorgt dafuer das die Elemente die erst noch (zukuenftig) kommen 
%  nur schwach angedeutet erscheinen 
%\beamersetuncovermixins{\opaqueness<1>{25}}{\opaqueness<2$\Rightarrow${15}}%here disabled
% klappt auch bei Tabellen, wenn teTeX verwendet wird\ldots
\renewcommand{\figurename}{}

\setbeamertemplate{footline}
{
  \leavevmode%
  \hbox{%
  \begin{beamercolorbox}[wd=.4\paperwidth,ht=2.25ex,dp=1ex,center]{author in head/foot}%
    \usebeamerfont{author in head/foot}\insertshorttitle
  \end{beamercolorbox}%
  \begin{beamercolorbox}[wd=.25\paperwidth,ht=2.25ex,dp=1ex,center]{title in head/foot}%
    \usebeamerfont{title in head/foot}\insertsection
  \end{beamercolorbox}%
  \begin{beamercolorbox}[wd=.3499\paperwidth,ht=2.25ex,dp=1ex,right]{date in head/foot}%
    \usebeamerfont{date in head/foot}\insertshortdate{}\hspace*{2em}
    \hyperlink{toc}{\insertframenumber{} / \inserttotalframenumber\hspace*{2ex}} 
  \end{beamercolorbox}}%
  \vskip0pt%
}

\usepackage[absolute,overlay]{textpos}
\usepackage{graphicx}

\newcommand{\source}[1]{\begin{textblock*}{9cm}(0.1cm,8.9cm)
    \begin{beamercolorbox}[ht=0.5cm,left]{framesource}
        \usebeamerfont{framesource}\usebeamercolor[fg!66]{framesource} Source: {#1}
    \end{beamercolorbox}
\end{textblock*}}


\begin{document}



%from file ../case1/data/000.txt
\begin{frame}[label=]
\frametitle{}
\begin{titlepage}

	\centering
	{\huge\bfseries \par}
	\vspace{2cm}
	{\LARGE\itshape Simon Kluettermann\par}
	\vspace{1.5cm}
	{\scshape\Large Master Thesis in Physics\par}
	\vspace{0.2cm}
	{\Large submitted to the \par}
	\vspace{0.2cm}
	{\scshape\Large Faculty of Mathematics Computer Science and Natural Sciences \par}
	\vspace{0.2cm}
	{\Large \par}
	\vspace{0.2cm}
	{\scshape\Large RWTH Aachen University}
	\vspace{1cm}
	
	\vfill
	{\scshape\Large Department of Physics\par}
	\vspace{0.2cm}
	{\scshape\Large Insitute for theoretical Particle Physics and Cosmology\par}
	\vspace{0.2cm}
	{ \Large\par}
	\vspace{0.2cm}
	{\Large First Referee: Prof. Dr. Michael Kraemer \par}
	{\Large Second Referee: Prof. Dr. Felix Kahlhoefer}

	\vfill

% Bottom of the page
	{\large November 2020 \par}
\end{titlepage}
\pagenumbering{roman}
\thispagestyle{empty}
\null
\newpage
\setcounter{page}{1}
\pagenumbering{arabic}
\end{frame}


%from file ../case1/data/001Anomaly Detection.txt
\begin{frame}[label=Anomaly Detection]
\frametitle{Anomaly Detection}
\begin{columns}[c] % align columns
\begin{column}{0.48\textwidth}%.48
\begin{itemize}

    \item Two distributions

\begin{itemize}

    \item One known (=normal)

    \item One unknown (=anomalies)


\end{itemize}
    \item Seperate them


\end{itemize}
\end{column}%
\hfill%
    \begin{column}{0.48\textwidth}%.48
\begin{figure}[H] 
  \centering
\includegraphics[width=0.9\textwidth]{..//prep/01Anomaly_Detection/anomalies.pdf}
\label{fig:prep01Anomaly_Detectionanomaliespdf}
  \end{figure}


\end{column}%
\hfill%
\end{columns}

\end{frame}


%from file ../case1/data/002Anomaly Detection.txt
\begin{frame}[label=Anomaly Detection]
\frametitle{Anomaly Detection}
\begin{columns}[c] % align columns
\begin{column}{0.48\textwidth}%.48
\begin{itemize}

    \item Two distributions

\begin{itemize}

    \item One known (=normal)

    \item One unknown (=anomalies)


\end{itemize}
    \item Seperate them

    \item Problem: few anomalies


\end{itemize}
\end{column}%
\hfill%
    \begin{column}{0.48\textwidth}%.48
\begin{figure}[H] 
  \centering
\includegraphics[width=0.9\textwidth]{..//prep/02Anomaly_Detection/difference.pdf}
\label{fig:prep02Anomaly_Detectiondifferencepdf}
  \end{figure}


\end{column}%
\hfill%
\end{columns}

\end{frame}


%from file ../case1/data/003Anomaly Detection.txt
\begin{frame}[label=Anomaly Detection]
\frametitle{Anomaly Detection}
\begin{columns}[c] % align columns
\begin{column}{0.48\textwidth}%.48
\begin{itemize}

    \item Anomalies are rare, so often only a few datapoints known (e.g. Machine Failure in an Aircraft)

    \item In practice, anomalies might appear that are not known during testing

    \item $\Rightarrow$So train the model only on normal samples

    \item Unsupervised Machine Learning

\begin{itemize}

    \item What can we say without knowing anomalies?

    \item ''Understand you dataset''


\end{itemize}

\end{itemize}
\end{column}%
\hfill%
    \begin{column}{0.48\textwidth}%.48
\begin{figure}[H] 
  \centering
\includegraphics[width=0.9\textwidth]{..//prep/03Anomaly_Detection/usup.pdf}
\label{fig:prep03Anomaly_Detectionusuppdf}
  \end{figure}


\end{column}%
\hfill%
\end{columns}

\end{frame}


%from file ../case1/data/004Anomaly Detection.txt
\begin{frame}[label=Anomaly Detection]
\frametitle{Anomaly Detection}
\begin{columns}[c] % align columns
\begin{column}{0.48\textwidth}%.48
\begin{itemize}

    \item Anomalies are rare, so often only a few datapoints known (e.g. Machine Failure in an Aircraft)

    \item In practice, anomalies might appear that are not known during testing

    \item $\Rightarrow$So train the model only on normal samples

    \item Unsupervised Machine Learning

\begin{itemize}

    \item What can we say without knowing anomalies?

    \item ''Understand you dataset''


\end{itemize}

\end{itemize}
\end{column}%
\hfill%
    \begin{column}{0.48\textwidth}%.48
\begin{figure}[H] 
  \centering
\includegraphics[width=0.9\textwidth]{..//prep/04Anomaly_Detection/circle.pdf}
\label{fig:prep04Anomaly_Detectioncirclepdf}
  \end{figure}


\end{column}%
\hfill%
\end{columns}

\end{frame}


%from file ../case1/data/005Anomaly Detection.txt
\begin{frame}[label=Anomaly Detection]
\frametitle{Anomaly Detection}
\begin{columns}[c] % align columns
\begin{column}{0.48\textwidth}%.48
\begin{itemize}

    \item Seems easy? Now do this

\begin{itemize}

    \item in thousands of dimensions

    \item with complicated distributions

    \item and overlap between anomalies and normal points


\end{itemize}

\end{itemize}
\end{column}%
\hfill%
    \begin{column}{0.48\textwidth}%.48
\begin{figure}[H] 
  \centering
\includegraphics[width=0.9\textwidth]{..//prep/05Anomaly_Detection/anomaly_detection.png}
\label{fig:prep05Anomaly_Detectionanomaly_detectionpng}
  \end{figure}


\end{column}%
\hfill%
\end{columns}

\end{frame}


%from file ../case1/data/006AutoML.txt
\begin{frame}[label=AutoML]
\frametitle{AutoML}
\begin{columns}[c] % align columns
\begin{column}{0.48\textwidth}%.48
\begin{itemize}

    \item Most machine learning requires Hyperparameter Optimisation

    \item (Find model parameters that result in the best results)

    \item $\Rightarrow$AutoML: Do this automatically as fast as possible


\end{itemize}
\end{column}%
\hfill%
    \begin{column}{0.48\textwidth}%.48
\begin{figure}[H] 
  \centering
\includegraphics[width=0.9\textwidth]{..//prep/06AutoML/Download.png}
\label{fig:prep06AutoMLDownloadpng}
  \end{figure}


\end{column}%
\hfill%
\end{columns}

\end{frame}


%from file ../case1/data/007AutoAD.txt
\begin{frame}[label=AutoAD]
\frametitle{AutoAD}
\begin{itemize}

    \item So lets combine both (Auto Anomaly Detection)

    \item $\Rightarrow$Problem

\begin{itemize}

    \item AutoMl requires Evaluation (loss, accuracy, AUC) to optimize

    \item AD can only be evaluated with regards to the anomalies

    \item $\Rightarrow$no longer unsupervised


\end{itemize}
    \item So most Anomaly Detection is ''unoptimized''


\end{itemize}
\end{frame}


%from file ../case1/data/008Solution 1 Metrics.txt
\begin{frame}[label=Solution 1 Metrics]
\frametitle{Solution 1 Metrics}
\begin{columns}[c] % align columns
\begin{column}{0.48\textwidth}%.48
\begin{itemize}

    \item So how to solve this?

    \item One option: Think of some function to evaluate only the normal points

    \item $\Rightarrow$A bit hard to do in a case study


\end{itemize}
\end{column}%
\hfill%
    \begin{column}{0.48\textwidth}%.48
\begin{figure}[H] 
  \centering
\includegraphics[width=0.9\textwidth]{..//prep/08Solution_1_Metrics/circle2.pdf}
\label{fig:prep08Solution_1_Metricscircle2pdf}
  \end{figure}


\end{column}%
\hfill%
\end{columns}

\end{frame}


%from file ../case1/data/009Solution 2 OneShot Learning.txt
\begin{frame}[label=Solution 2 OneShot Learning]
\frametitle{Solution 2 OneShot Learning}
\begin{itemize}

    \item So how to solve this?

    \item One option: ''Just find the best solution directly''

    \item $\Rightarrow$Zero Shot AutoML

    \item Find best practices for hyperparameters

    \item Requires optimisation for each model seperately $\Rightarrow$ matches the case study structure quite well!


\end{itemize}
\end{frame}


%from file ../case1/data/010Course.txt
\begin{frame}[label=Course]
\frametitle{Course}
\begin{columns}[c] % align columns
\begin{column}{0.48\textwidth}%.48
\begin{itemize}

    \item Basics of Scientific Computing

    \item Basics of AD

    \item Basics of AutoML

    \item Build groups for each algorithm

\begin{itemize}

    \item Choose a set of Hyperparameters

    \item Find ''best practice`s'' for them

    \item Maybe consider more complicated Transformations (Preprocessing, Ensemble)


\end{itemize}
    \item Compare between groups (best algorithm for current situation)

    \item Evaluate on new datasets

    \item Write a report/Present your work


\end{itemize}
\end{column}%
\hfill%
    \begin{column}{0.48\textwidth}%.48
\begin{figure}[H] 
  \centering
\includegraphics[width=0.9\textwidth]{..//prep/09Course/table.png}
\label{fig:prep09Coursetablepng}
  \end{figure}


\end{column}%
\hfill%
\end{columns}

\end{frame}


%from file ../case1/data/011Questions.txt
\begin{frame}[label=Questions]
\frametitle{Questions}
\begin{itemize}

    \item Requirements:

\begin{itemize}

    \item MD Req 1$\Rightarrow$MD Req 8

    \item Basic Python/Math Knowledge

    \item Motivation to learn something new;)


\end{itemize}

\end{itemize}
\end{frame}



\end{document}