Add Basics of Traditional Network learning via BP (#18)

* Add Basics of Traditional Network learning via BP

* Fix file paths

* Add apostrophe

main.tex

@@ -39,12 +39,12 @@
 
 	\section{Introduction to neural networks}
 		\subsection{What is a neural network?}
-			\subfile{sections/"Introduction to neural networks/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}
-				.
+				\subfile{sections/"introduction to neural networks/how does a neural network learn/traditiontal"}
 			\subsubsection{Genetic algorithm}
-				\subfile{sections/"Introduction to neural networks/How does a neural network learn/genetic algorithm"}
+				\subfile{sections/"introduction to neural networks/how does a neural network learn/genetic algorithm"}
 	\newpage
 
 	\section{What is NEAT}

resources/bibliography.bib

@@ -176,6 +176,14 @@ @Electronic{Urologie
   Timestamp                = {21.05.2015}
 }
 
+@Electronic{backprop_from_scratch,
+  author    = {Json Brownlee},
+  year      = {2016},
+  title     = {How to Implement the Backpropagation Algorithm From Scratch In Python},
+  url       = {http://machinelearningmastery.com/implement-backpropagation-algorithm-scratch-python/},
+  timestamp = {07.11.2016},
+}
+
 @Electronic{DDSM,
   Title                    = {Digital Database for Screening Mammography},
   Author                   = {University of South Florida},
@@ -212,5 +220,3 @@ @Electronic{Kardiologie
   Timestamp                = {01.03.2016}
 }
 
-@comment{jabref-meta: databaseType:bibtex;}
-

sections/introduction to neural networks/how does a neural network learn/traditiontal.tex

@@ -0,0 +1,9 @@
+The traditional approach of optimizing the connection weigths to improve the network's accuracy is named backpropagation.
+
+\begin{quote}
+\emph{"The Backpropagation algorithm is a supervised learning method for multilayer feed-forward networks from the field of Artificial Neural Networks. }
+
+\emph{Feed-forward neural networks are inspired by the information processing of one or more neural cells, called a neuron. A neuron accepts input signals via its dendrites, which pass the electrical signal down to the cell body. The axon carries the signal out to synapses, which are the connections of a cell’s axon to other cell’s dendrites."} \cite{backprop_from_scratch} 
+\end{quote}
+
+Backpropagation uses mathematical approaches to calculate changes to the weights of its connections, so that the output becomes more accurate every time the weights are updated.