Add table of contents (#13)

IDPA16 · Nov 20, 2016 · f83d781 · f83d781
1 parent e1bd34a
commit f83d781
Show file tree

Hide file tree

Showing 3 changed files with 81 additions and 9 deletions.
diff --git a/main.tex b/main.tex
@@ -14,7 +14,6 @@
 
 \setlength{\parindent}{0pt}
 \setlength{\parskip}{1em}
-\setstretch{1.136363636} % required 1.5pt spacing
 
 \makeatletter
 \renewcommand\@biblabel[1]{#1.}
@@ -30,20 +29,97 @@
 \newpage
 
 \begin{abstract}
-	
+
 	\newpage
-	
+
 \end{abstract}
 
 	\tableofcontents
 	\newpage
 
 	\section{Introduction to neural networks}
-	\subfile{sections/"what is a neural network"}
-	\subfile{sections/"how does a neural network learn"}
+		\subsection{What is a neural network?}
+			\subfile{sections/"Introduction to neural networks/what is a neural network"}
+		\subsection{How does a neural network learn}
+			\subsubsection{Traditional}
+				.
+			\subsubsection{Genetic algorithm}
+				\subfile{sections/"Introduction to neural networks/How does a neural network learn/genetic algorithm"}
+	\newpage
+
+	\section{What is NEAT}
+		\subsection{Topology}
+			.
+		\subsection{Speciation}
+			.
+	\newpage
+
+	\section{Convolutional Neural Networks}
+		\subsection{Problems with image recognition}
+			.
+		\subsection{Subsampling}
+			\subsubsection{Kernels}
+				.
+			\subsubsection{Poolers}
+				.
+		\subsection{Structure}
+			.
+	\newpage
 
+	\section{Hippocrates, a NEAT implementation}
+		\subsection{Motivation}
+			.
+		\subsection{Discrepancies}
+			\subsubsection{Paper}
+				.
+			\subsubsection{Original implementation}
+				.
+		\subsection{Convolutional module}
+			.
+		\subsection{Visualizing Neural Networks}
+			.
 	\newpage
 
+	\section{Build tools}
+		\subsection{Version control}
+			\subsubsection{Git}
+				.
+			\subsubsection{GitHub}
+				.
+		\subsection{Integration tests}
+			\subsubsection{Travis}
+				.
+			\subsubsection{AppVeyor}
+				.
+	\newpage
+
+	\section{Combining Neuro-Evolution of Augmenting Topologies with Convolutional Neural Networks}
+		\subsection{Possibilities of modeling}
+			.
+		\subsection{Challenges}
+			.
+		\subsection{Solutions}
+			.
+		\subsection{Implementation}
+			.
+	\newpage
+
+	\section{Results}
+		\subsection{Benchmarks}
+			.
+	\newpage
+
+	\section{Further enhancements}
+		\subsection{Safety concerns}
+			.
+		\subsection{HyperNEAT}
+			.
+	\newline
+
+	\section{Collaborators}
+		.
+	\newline
+
 	\nocite{*}
 	{\RaggedRight
 		\bibliography{resources/bibliography}

diff --git a/sections/how does a neural network learn.tex → ...eural network learn/genetic algorithm.tex b/sections/how does a neural network learn.tex → ...eural network learn/genetic algorithm.tex
@@ -1,5 +1,3 @@
-\subsection{How does a neural network learn?}
-
 The training starts with a number of genomes, typically referred to as the population. For each of these genomes a network is built and it is tested against the expected outputs. From these results we can assign a fitness to the genome. A higher fitness indicates that the genome was able to solve a problem better than another. \cite{Anderson1995}
 
 The initial set of genes is the first generation. The weights of all genes are set to a random value.

diff --git a/sections/what is a neural network.tex → ...ral networks/what is a neural network.tex b/sections/what is a neural network.tex → ...ral networks/what is a neural network.tex
@@ -1,5 +1,3 @@
-\subsection{What is a neural network?}
-
 A neural network follows the “divide and conquer” principle. It consists of two simple components: neurons and connections.
 
 Each neuron has inputs, which are the incoming connections. It applies a simple mathematical operation to this set of inputs and returns the result.