general structure and project goal

LaTeX/Final_Project_Loedige.tex

@@ -1,4 +1,10 @@
 \documentclass[a4paper, 12pt, english]{article}
+\usepackage[
+    top=2cm,
+    bottom=2cm,
+    right=2cm,
+    left=2cm
+]{geometry}
 
 \usepackage[utf8]{inputenc}
 \usepackage[T1]{fontenc}
@@ -8,6 +14,7 @@
 \usepackage{multicol}
 \usepackage{setspace}
 \usepackage{graphicx}
+\usepackage{xurl}
 
 % allow deeeep lists
 \usepackage{enumitem}
@@ -46,6 +53,7 @@
 \begin{document}
 \maketitle
 \toccontents
+\clearpage
 
 \section{Assignment}%
 \label{sec:Assignment}
@@ -104,103 +112,67 @@
         \item Put all the above in a single PDF and upload to ITC-LMS
     \end{itemize}
 \end{itemize}
-
-\subsection{How the project is graded}%
-\label{sub:How the project is graded}
-\begin{itemize}
-    \item The purpose of the project is to make you familiar with machine learning experiments.
-    \begin{itemize}
-        \item Not intended to be a stressful project.
-        \begin{itemize}
-            \item So do not worry too much on achieving high accuracy, good parameter settings, etc
-            \item Make sure to keep it simple
-        \end{itemize}
-    \end{itemize}
-    \item What we would like to see:
-    \begin{itemize}
-        \item Clarity of the project description
-        \item Relevance between the problem and the chosen approaches
-        \item Appropriate input/output design and execution of the experiments
-        \item Proper evaluation methods, figures and tables
-        \item Easy to understand writings, informative comments on the code
-    \end{itemize}
-    \item Overall grade for this course : 70\% homeworks, 30\% final project
-    \begin{itemize}
-        \item Bonus points for helping each other on slack
-        \begin{itemize}
-            \item Feel free to discuss your final project on slack if you have troubles
-        \end{itemize}
-    \end{itemize}
-\end{itemize}
 \clearpage
 
-%\section{Code}%
-%\label{sec:Code}
+\section{Project Goal}%
+\label{sec:Project Goal}
+This project aims to compare different deep learning techniques.
+The goal is to discern the pros and cons of the different techniques when it comes to their use on character recognitions in images.
+This approach was chosen because it doesn't focus on the learning of object concepts but rather on pattern recognition.
+Since pattern recognition and character recognition in particular is a less complex topic than concept classification
+it allows for the use of less complex models which are easier to understand.
 
-%\definecolor{mGreen}{rgb}{0,0.6,0}
-%\definecolor{mGray}{rgb}{0.5,0.5,0.5}
-%\definecolor{mPurple}{rgb}{0.58,0,0.82}
-%\definecolor{backgroundColour}{rgb}{0.95,0.95,0.92}
-%\lstset{
-    %language=C,
-    %backgroundcolor=\color{backgroundColour},   
-    %commentstyle=\color{mGreen},
-    %keywordstyle=\color{magenta},
-    %numberstyle=\tiny\color{mGray},
-    %stringstyle=\color{mPurple},
-    %basicstyle=\ttfamily\scriptsize,
-    %breakatwhitespace=false,         
-    %breaklines=true,                 
-    %captionpos=b,                    
-    %keepspaces=true,                 
-    %numbers=left,                    
-    %firstnumber=0,
-    %stepnumber=1,
-    %numbersep=5pt,                  
-    %showspaces=false,                
-    %showstringspaces=false,
-    %showtabs=false,                  
-    %tabsize=2,
-    %literate={~}{{$\mathtt{\sim}$}}1
-%}
-%\lstset{literate=%
-    %{Ö}{{\"O}}1
-    %{Ä}{{\"A}}1
-    %{Ü}{{\"U}}1
-    %{ß}{{\ss}}2
-    %{ü}{{\"u}}1
-    %{ä}{{\"a}}1
-    %{ö}{{\"o}}1
-%}
+\subsection{The Dataset}%
+\label{sub:The Dataset}
+The project uses the "svhn\_cropped" dataset (\url{https://www.tensorflow.org/datasets/catalog/svhn_cropped}).
+The Street View House Numbers (SVHN) dataset was created at Stanford University and includes 
+"73\,257 digits for training, 26\,032 digits for testing, 
+and 531\,131 additional, somewhat less difficult samples, to use as extra training data" (\url{http://ufldl.stanford.edu/housenumbers/}).
+The dataset provided by TensorFlow uses the "MNIST-like 32-by-32 images centered around a single character" version.
 
-%\subsection{\texttt{vinput.c}}%
-%\label{sub:vinput_c}
-%\lstinputlisting{../Code/vinput.c}
-%\clearpage
+\clearpage
 
-%\subsection{\texttt{vinput.h}}%
-%\label{sub:vinput_h}
-%\lstinputlisting{../Code/vinput.h}
-%\clearpage
+\section{Code}%
+\label{sec:Code}
 
-%\subsection{\texttt{vkbd.c}}%
-%\label{sub:vkbd}
-%\lstinputlisting{../Code/vkbd.c}
-%\clearpage
+The following code is an exported and slightly formatted version of a Jupyter Notebook that is also available at \url{https://git.ploedige.com/Intelligent_World_Informatics_V/Final_Project}.
 
-%\section{Output}%
-%\label{sec:Output}
+\definecolor{mGreen}{rgb}{0,0.6,0}
+\definecolor{mGray}{rgb}{0.5,0.5,0.5}
+\definecolor{mPurple}{rgb}{0.58,0,0.82}
+\definecolor{backgroundColour}{rgb}{0.95,0.95,0.92}
+\lstset{
+    language=python,
+    backgroundcolor=\color{backgroundColour},   
+    commentstyle=\color{mGreen},
+    keywordstyle=\color{magenta},
+    numberstyle=\tiny\color{mGray},
+    stringstyle=\color{mPurple},
+    basicstyle=\ttfamily\scriptsize,
+    breakatwhitespace=false,         
+    breaklines=true,                 
+    captionpos=b,                    
+    keepspaces=true,                 
+    numbers=left,                    
+    firstnumber=0,
+    stepnumber=1,
+    numbersep=5pt,                  
+    showspaces=false,                
+    showstringspaces=false,
+    showtabs=false,                  
+    tabsize=2,
+    literate={~}{{$\mathtt{\sim}$}}1
+}
+\lstset{literate=%
+    {Ö}{{\"O}}1
+    {Ä}{{\"A}}1
+    {Ü}{{\"U}}1
+    {ß}{{\ss}}2
+    {ü}{{\"u}}1
+    {ä}{{\"a}}1
+    {ö}{{\"o}}1
+}
 
-%\subsection{Shell Script for compiling and running}%
-%\label{sub:Shell Script for compiling and running}
-%\includegraphics[width=\textwidth]{run_sh.png}
-
-%\subsection{Terminal Screenshot}%
-%\label{sub:Terminal Screenshot}
-%\includegraphics[width=\textwidth]{executing_screenshot.png}
-
-%\subsection{\texttt{output.txt}}%
-%\label{sub:output_txt}
-%\includegraphics[width=\textwidth]{output_txt.png}
+\lstinputlisting{./exported_code.py}
 
 \end{document}