192 lines
24 KiB
TeX
Executable file
192 lines
24 KiB
TeX
Executable file
\relax
|
|
\providecommand\hyper@newdestlabel[2]{}
|
|
\catcode `"\active
|
|
\providecommand\HyperFirstAtBeginDocument{\AtBeginDocument}
|
|
\HyperFirstAtBeginDocument{\ifx\hyper@anchor\@undefined
|
|
\global\let\oldcontentsline\contentsline
|
|
\gdef\contentsline#1#2#3#4{\oldcontentsline{#1}{#2}{#3}}
|
|
\global\let\oldnewlabel\newlabel
|
|
\gdef\newlabel#1#2{\newlabelxx{#1}#2}
|
|
\gdef\newlabelxx#1#2#3#4#5#6{\oldnewlabel{#1}{{#2}{#3}}}
|
|
\AtEndDocument{\ifx\hyper@anchor\@undefined
|
|
\let\contentsline\oldcontentsline
|
|
\let\newlabel\oldnewlabel
|
|
\fi}
|
|
\fi}
|
|
\global\let\hyper@last\relax
|
|
\gdef\HyperFirstAtBeginDocument#1{#1}
|
|
\providecommand\HyField@AuxAddToFields[1]{}
|
|
\providecommand\HyField@AuxAddToCoFields[2]{}
|
|
\abx@aux@refcontext{nty/global//global/global}
|
|
\@writefile{toc}{\boolfalse {citerequest}\boolfalse {citetracker}\boolfalse {pagetracker}\boolfalse {backtracker}\relax }
|
|
\@writefile{lof}{\boolfalse {citerequest}\boolfalse {citetracker}\boolfalse {pagetracker}\boolfalse {backtracker}\relax }
|
|
\@writefile{lot}{\boolfalse {citerequest}\boolfalse {citetracker}\boolfalse {pagetracker}\boolfalse {backtracker}\relax }
|
|
\babel@aux{ngerman}{}
|
|
\abx@aux@cite{1}
|
|
\abx@aux@segm{0}{0}{1}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {section}{\numberline {1}Was ist maschinelles Lernen?}{3}{section.1}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {1.1}Klassifizierungsaufgaben}{3}{subsection.1.1}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces Die zwei Klassen w\IeC {\"a}ren hier \glqq gr\IeC {\"u}n'' und \glqq blau''. Die Linie stellt die Klassengrenze dar, die die zwei Klassen unterscheidet. Es sind au\IeC {\ss }erdem einige Ausrei\IeC {\ss }er in den Daten vorhanden. \relax }}{4}{figure.caption.2}\protected@file@percent }
|
|
\providecommand*\caption@xref[2]{\@setref\relax\@undefined{#1}}
|
|
\newlabel{Classification}{{1}{4}{Die zwei Klassen wären hier \glqq grün'' und \glqq blau''. Die Linie stellt die Klassengrenze dar, die die zwei Klassen unterscheidet. Es sind außerdem einige Ausreißer in den Daten vorhanden. \relax }{figure.caption.2}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {1.2}Regressionsprobleme}{4}{subsection.1.2}\protected@file@percent }
|
|
\abx@aux@cite{4}
|
|
\abx@aux@segm{0}{0}{4}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces Die Kurve stellt hier keine Grenze, sondern die Funktion, die die Werte approximiert, dar. Die Punkte repr\IeC {\"a}sentieren die Eingabedaten, wobei auch hier einige Ausrei\IeC {\ss }er erkennbar sind.\relax }}{5}{figure.caption.3}\protected@file@percent }
|
|
\newlabel{Regression}{{2}{5}{Die Kurve stellt hier keine Grenze, sondern die Funktion, die die Werte approximiert, dar. Die Punkte repräsentieren die Eingabedaten, wobei auch hier einige Ausreißer erkennbar sind.\relax }{figure.caption.3}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {1.3}Gefahren von maschinellem Lernen}{5}{subsection.1.3}\protected@file@percent }
|
|
\abx@aux@cite{5}
|
|
\abx@aux@segm{0}{0}{5}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsubsection}{\numberline {1.3.1}Datens\IeC {\"a}tze f\IeC {\"u}r maschinelles Lernen}{6}{subsubsection.1.3.1}\protected@file@percent }
|
|
\abx@aux@cite{8}
|
|
\abx@aux@segm{0}{0}{8}
|
|
\abx@aux@cite{9}
|
|
\abx@aux@segm{0}{0}{9}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsubsection}{\numberline {1.3.2}Overfitting}{7}{subsubsection.1.3.2}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {3}{\ignorespaces Klassengrenzen mit und ohne Overfitting\relax }}{7}{figure.caption.4}\protected@file@percent }
|
|
\newlabel{Overfitting}{{3}{7}{Klassengrenzen mit und ohne Overfitting\relax }{figure.caption.4}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {1.4}Adversarial attacks}{7}{subsection.1.4}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {section}{\numberline {2}Verschiedene Techniken maschinellen Lernens}{8}{section.2}\protected@file@percent }
|
|
\newlabel{sec:verschiedene-techniken-maschinellen-lernens}{{2}{8}{Verschiedene Techniken maschinellen Lernens}{section.2}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}\IeC {\"U}berwachtes Lernen}{8}{subsection.2.1}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Un\IeC {\"u}berwachtes Lernen}{8}{subsection.2.2}\protected@file@percent }
|
|
\abx@aux@cite{2}
|
|
\abx@aux@segm{0}{0}{2}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Best\IeC {\"a}rkendes Lernen}{9}{subsection.2.3}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {section}{\numberline {3}Neuronale Netze}{9}{section.3}\protected@file@percent }
|
|
\newlabel{sec:neuronale-netze}{{3}{9}{Neuronale Netze}{section.3}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Maschinelles Lernen und menschliches Lernen}{9}{subsection.3.1}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {4}{\ignorespaces Neuron \newline Quelle: simple.wikipedia.org/wiki/File:Neuron.svg\newline Copyright: CC Attribution-Share Alike von Nutzer Dhp1080,\newline bearbeitet}}{10}{figure.caption.5}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}Der Aufbau eines neuronalen Netzes}{10}{subsection.3.2}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {5}{\ignorespaces Schematische Darstellung eines einfachen neuronalen Netzes\relax }}{11}{figure.caption.6}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {3.3}Berechnung des Ausgabevektors}{12}{subsection.3.3}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {6}{\ignorespaces Darstellung der Sigmoid-Funktion $\sigma (x)=\frac {e^x}{e^x+1}$ im Intervall $[-5, 5]$\relax }}{12}{figure.caption.7}\protected@file@percent }
|
|
\newlabel{Sigmoid}{{6}{12}{Darstellung der Sigmoid-Funktion $\sigma (x)=\frac {e^x}{e^x+1}$ im Intervall $[-5, 5]$\relax }{figure.caption.7}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {7}{\ignorespaces Formel zur Berechnung eines Ausgabevektors aus einem Eingabevektor durch eine Schicht von Neuronen. \relax }}{14}{figure.caption.8}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {3.4}Der Lernprozess}{14}{subsection.3.4}\protected@file@percent }
|
|
\abx@aux@cite{3}
|
|
\abx@aux@segm{0}{0}{3}
|
|
\abx@aux@segm{0}{0}{3}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {3.5}Fehlerfunktionen}{15}{subsection.3.5}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.1}MSE -- Durchschnittlicher quadratischer Fehler}{15}{subsubsection.3.5.1}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {8}{\ignorespaces Die Gleichung f\IeC {\"u}r den durchschnittlichen quadratischen Fehler\relax }}{15}{figure.caption.9}\protected@file@percent }
|
|
\newlabel{MSE_equation}{{8}{15}{Die Gleichung für den durchschnittlichen quadratischen Fehler\relax }{figure.caption.9}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.2}MAE -- Durchschnittlicher absoluter Fehler}{15}{subsubsection.3.5.2}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {9}{\ignorespaces Die Gleichung f\IeC {\"u}r den durchschnittlichen absoluten Fehler\relax }}{16}{figure.caption.10}\protected@file@percent }
|
|
\newlabel{MAE_equation}{{9}{16}{Die Gleichung für den durchschnittlichen absoluten Fehler\relax }{figure.caption.10}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.3}Kreuzentropiefehler}{16}{subsubsection.3.5.3}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {10}{\ignorespaces Der Graph der Kreuzentropie-Fehlerfunktion, wenn das tats\IeC {\"a}chliche Label 1 ist\relax }}{16}{figure.caption.11}\protected@file@percent }
|
|
\newlabel{CEL_Graph}{{10}{16}{Der Graph der Kreuzentropie-Fehlerfunktion, wenn das tatsächliche Label 1 ist\relax }{figure.caption.11}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {11}{\ignorespaces Die Gleichung f\IeC {\"u}r den Kreuzentropiefehler\relax }}{17}{figure.caption.12}\protected@file@percent }
|
|
\newlabel{CEL_Function}{{11}{17}{Die Gleichung für den Kreuzentropiefehler\relax }{figure.caption.12}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {12}{\ignorespaces Die Gleichung f\IeC {\"u}r den durchschnittlichen absoluten Fehler\relax }}{17}{figure.caption.13}\protected@file@percent }
|
|
\newlabel{CEL_Function_cummulative}{{12}{17}{Die Gleichung für den durchschnittlichen absoluten Fehler\relax }{figure.caption.13}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {3.6}Gradientenverfahren und Backpropagation}{17}{subsection.3.6}\protected@file@percent }
|
|
\newlabel{Gradient_section}{{3.6}{17}{Gradientenverfahren und Backpropagation}{subsection.3.6}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {13}{\ignorespaces Die Gleichung f\IeC {\"u}r den Gradienten der Fehlerfunktion\relax }}{18}{figure.caption.14}\protected@file@percent }
|
|
\newlabel{Gradient_Function}{{13}{18}{Die Gleichung für den Gradienten der Fehlerfunktion\relax }{figure.caption.14}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.6.1}Lernrate}{18}{subsubsection.3.6.1}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {14}{\ignorespaces Die Gleichung f\IeC {\"u}r die Anpassung eines einzelnen Parameters\relax }}{18}{figure.caption.15}\protected@file@percent }
|
|
\newlabel{Learning_Rate_Function}{{14}{18}{Die Gleichung für die Anpassung eines einzelnen Parameters\relax }{figure.caption.15}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {15}{\ignorespaces $\eta $ ist hier zu gro\IeC {\ss } gew\IeC {\"a}hlt, sodass das Minimum stets \IeC {\"u}bersprungen wird.\relax }}{19}{figure.caption.16}\protected@file@percent }
|
|
\newlabel{Learning_Rate_Graphic}{{15}{19}{$\eta $ ist hier zu groß gewählt, sodass das Minimum stets übersprungen wird.\relax }{figure.caption.16}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {3.7}Verschiedene Layerarten}{19}{subsection.3.7}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.7.1}Convolutional Layers}{19}{subsubsection.3.7.1}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {16}{\ignorespaces Eine Verbildlichung der Vorg\IeC {\"a}nge in einem convolutional Layer\newline Aus einer Animation von\newline https://github.com/vdumoulin/conv\_arithmetic/blob/master/README.md Vincent Dumoulin, Francesco Visin - A guide to convolution arithmetic for deep learning (BibTeX)}}{20}{figure.caption.17}\protected@file@percent }
|
|
\newlabel{Convolution_illustration}{{16}{20}{Eine Verbildlichung der Vorgänge in einem convolutional Layer\newline Aus einer Animation von\newline https://github.com/vdumoulin/conv\_arithmetic/blob/master/README.md\\ Vincent Dumoulin, Francesco Visin - A guide to convolution arithmetic for deep learning (BibTeX)}{figure.caption.17}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {17}{\ignorespaces Erkennt obere horizontale Kanten\relax }}{20}{figure.caption.18}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {18}{\ignorespaces Erkennt linke vertikale Kanten\relax }}{20}{figure.caption.18}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {19}{\ignorespaces Erkennt untere horizontale Kanten\relax }}{20}{figure.caption.18}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {20}{\ignorespaces Erkennt rechte vertikale Kanten\relax }}{20}{figure.caption.18}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {21}{\ignorespaces Das Beispielbild aus dem Mnist Datensatz\relax }}{21}{figure.caption.19}\protected@file@percent }
|
|
\newlabel{Filter_Example_raw}{{21}{21}{Das Beispielbild aus dem Mnist Datensatz\relax }{figure.caption.19}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {22}{\ignorespaces Die jeweils oben stehenden Filter wurden auf das Beispielbild angewandt.\relax }}{21}{figure.caption.20}\protected@file@percent }
|
|
\newlabel{Filter_output dargestellt}{{22}{21}{Die jeweils oben stehenden Filter wurden auf das Beispielbild angewandt.\relax }{figure.caption.20}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {23}{\ignorespaces Beispiele f\IeC {\"u}r low-, mid- und high-level Features in Convolutional Neural Nets\newline Quelle: https://tvirdi.github.io/2017-10-29/cnn/}}{22}{figure.caption.21}\protected@file@percent }
|
|
\newlabel{HL_features_conv}{{23}{22}{Beispiele für low-, mid- und high-level Features in Convolutional Neural Nets\newline Quelle: https://tvirdi.github.io/2017-10-29/cnn/}{figure.caption.21}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.7.2}Pooling Layers}{22}{subsubsection.3.7.2}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {24}{\ignorespaces Max Pooling mit $2\times 2$ gro\IeC {\ss }en Submatrizen\newline Quelle: https://computersciencewiki.org/index.php/Max-pooling\_/\_Pooling CC BY NC SA Lizenz}}{23}{figure.caption.22}\protected@file@percent }
|
|
\newlabel{Maxpool}{{24}{23}{Max Pooling mit $2\times 2$ großen Submatrizen\newline Quelle: https://computersciencewiki.org/index.php/Max-pooling\_/\_Pooling\\ CC BY NC SA Lizenz}{figure.caption.22}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {25}{\ignorespaces Average-Pooling mit $2\times 2$ gro\IeC {\ss }en Submatrizen\newline Aus: Dominguez-Morales, Juan Pedro. (2018). Neuromorphic audio processing through real-time embedded spiking neural networks. Abbildung 33}}{23}{figure.caption.23}\protected@file@percent }
|
|
\newlabel{AvgPool}{{25}{23}{Average-Pooling mit $2\times 2$ großen Submatrizen\newline Aus: Dominguez-Morales, Juan Pedro. (2018). Neuromorphic audio processing through real-time embedded spiking neural networks. Abbildung 33}{figure.caption.23}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {26}{\ignorespaces Gegen\IeC {\"u}berstellung von Max- und Average-Pooling\relax }}{24}{figure.caption.24}\protected@file@percent }
|
|
\newlabel{Pooling_Mnist}{{26}{24}{Gegenüberstellung von Max- und Average-Pooling\relax }{figure.caption.24}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {section}{\numberline {4}PyTorch}{24}{section.4}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {4.1}Datenvorbereitung}{25}{subsection.4.1}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {27}{\ignorespaces Der Code zum Laden des MNIST Datensatzes\relax }}{26}{figure.caption.25}\protected@file@percent }
|
|
\newlabel{MNIST_Dataloader_Code}{{27}{26}{Der Code zum Laden des MNIST Datensatzes\relax }{figure.caption.25}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {4.2}Definieren des Netzes}{27}{subsection.4.2}\protected@file@percent }
|
|
\abx@aux@cite{6}
|
|
\abx@aux@segm{0}{0}{6}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {28}{\ignorespaces Code, um ein einfaches Netz in Pytorch zu definieren\relax }}{28}{figure.caption.26}\protected@file@percent }
|
|
\newlabel{Net_simple_definition}{{28}{28}{Code, um ein einfaches Netz in Pytorch zu definieren\relax }{figure.caption.26}{}}
|
|
\abx@aux@cite{7}
|
|
\abx@aux@segm{0}{0}{7}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {4.3}Trainieren des Netzes}{29}{subsection.4.3}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {29}{\ignorespaces Code, um das Netz auf einem Datensatz zu trainieren\relax }}{29}{figure.caption.27}\protected@file@percent }
|
|
\newlabel{Code_train_loop}{{29}{29}{Code, um das Netz auf einem Datensatz zu trainieren\relax }{figure.caption.27}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {4.4}Pytorch und weights and biases}{31}{subsection.4.4}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {section}{\numberline {5}Ein Klassifizierungsnetzwerk f\IeC {\"u}r handgeschriebene Ziffern}{31}{section.5}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {5.1}Aufgabe}{31}{subsection.5.1}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {5.2}Der MNIST Datensatz}{31}{subsection.5.2}\protected@file@percent }
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {5.3}Das Netz}{32}{subsection.5.3}\protected@file@percent }
|
|
\newlabel{sec:das-netz}{{5.3}{32}{Das Netz}{subsection.5.3}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {30}{\ignorespaces Der Code, um das in diesem Projekt genutzte Klassifizierungsnetz zu definieren.\relax }}{32}{figure.caption.28}\protected@file@percent }
|
|
\newlabel{net}{{30}{32}{Der Code, um das in diesem Projekt genutzte Klassifizierungsnetz zu definieren.\relax }{figure.caption.28}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {31}{\ignorespaces Der Graph der ReLu Aktivierungsfunktion\relax }}{33}{figure.caption.29}\protected@file@percent }
|
|
\newlabel{ReLu}{{31}{33}{Der Graph der ReLu Aktivierungsfunktion\relax }{figure.caption.29}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {subsection}{\numberline {5.4}Ergebnis}{33}{subsection.5.4}\protected@file@percent }
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {32}{\ignorespaces Ein Plot der Trefferquote, aufgetragen gegen die Trainingszeit\relax }}{34}{figure.caption.30}\protected@file@percent }
|
|
\newlabel{accuracy}{{32}{34}{Ein Plot der Trefferquote, aufgetragen gegen die Trainingszeit\relax }{figure.caption.30}{}}
|
|
\@writefile{lof}{\defcounter {refsection}{0}\relax }\@writefile{lof}{\contentsline {figure}{\numberline {33}{\ignorespaces Ein Plot des Kreuzentropiefehlers aufgetragen gegen die Trainingszeit\relax }}{34}{figure.caption.31}\protected@file@percent }
|
|
\newlabel{loss}{{33}{34}{Ein Plot des Kreuzentropiefehlers aufgetragen gegen die Trainingszeit\relax }{figure.caption.31}{}}
|
|
\@writefile{toc}{\defcounter {refsection}{0}\relax }\@writefile{toc}{\contentsline {section}{\numberline {6}Schluss}{35}{section.6}\protected@file@percent }
|
|
\bibcite{1}{1}
|
|
\bibcite{2}{2}
|
|
\bibcite{3}{3}
|
|
\bibcite{4}{4}
|
|
\bibcite{5}{5}
|
|
\bibcite{6}{6}
|
|
\bibcite{7}{7}
|
|
\bibcite{8}{8}
|
|
\bibcite{9}{9}
|
|
\gdef\minted@oldcachelist{,
|
|
default-pyg-prefix.pygstyle,
|
|
default.pygstyle,
|
|
3689BC65F2D8327A52B99A4D4543798E53A0C9FE66949F8EC4BED65B31F6975B.pygtex,
|
|
A4B374C1656F7019947BB217D7D8C34BF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
6E136E4601877EDF7BAFA4E113440C09F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
269EB77B41B74A0DDA1E98D8C4CCFD9DF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
9B331F10CD24BEF694DFB75FBF495B69F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
E569CCE4C53760D94B3D7D8143D84D55F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
FAA14B25340C2458FD5D369A042116ABF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
745405EA92794205A61C3062FFF26B3CF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
2310AA0C124794A026E719F78EC1B44DF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
EDB0BACF1F2CD448B8D22F1A9B4F026EF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
9A791CC5219F6F4D627591113AE747DBF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
090D83D976E5CEECA0A0961BB3B3A5A6F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
12F96C5C5DB151598C41F68BDCE383E2F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
7C08F8DDD5F5D41169EB51C2ADB3E0B1F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
D6B06E011A4BC083034B9BD6480B9AB253A0C9FE66949F8EC4BED65B31F6975B.pygtex,
|
|
7572134CCA2BA7D050325F33C4941E41F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
689375EA3B9C38D437AA368912E13885F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
B68FDDAFFF09CEFEB070EDD4AD4C96E1F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
B68FDDAFFF09CEFEB070EDD4AD4C96E1F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
689375EA3B9C38D437AA368912E13885F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
7C08F8DDD5F5D41169EB51C2ADB3E0B1F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
7572134CCA2BA7D050325F33C4941E41F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
7572134CCA2BA7D050325F33C4941E41F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
689375EA3B9C38D437AA368912E13885F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
6361598B18370336863B24D1B6FAE96EF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
7C08F8DDD5F5D41169EB51C2ADB3E0B1F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
5A0B7618927FB8AEA4B96F5552228CD8F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
966BC12992AE07118A5C030A258708A853A0C9FE66949F8EC4BED65B31F6975B.pygtex,
|
|
6843D04ED2E2C37F8AF3EB0462FB514BF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
00B37D79FD3312AD6F59A2B37BA81087F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
684559E268B2B047D1C82BB00E985301F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
ECDE410C14A506CF9F77A687B26F5474F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
30299FD7E2187F6D53ED8A608F3958F2F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
458D5F1AFC81AE7291A7AAAD852DC12AF6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
B51E2DE1996D35173C012720F7A4FDA4F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex,
|
|
91DA331C052E3A07FD9B933AC7C049B253A0C9FE66949F8EC4BED65B31F6975B.pygtex,
|
|
A26181649063E5A564A34B0EBDE29E28F6C426F58C5CCC27D3C7BD698FEC22DB.pygtex}
|