clara/pytorch-ai
1
0
Fork 0
Code Issues 1 Pull requests Projects Releases Packages Wiki Activity Actions

Added chapters, trained net

Browse source
This commit is contained in:
Clemens Dautermann 2019-12-27 20:08:35 +01:00
parent 9350b1e4ba
commit a3f984996c
30 changed files with 1134 additions and 934 deletions
Download patch file Download diff file Expand all files Collapse all files

44
doc/Grundlagen_des_maschinellen_lernens.out
View file

@ -5,26 +5,24 @@
\BOOKMARK [2][-]{subsection.2.2}{Der Aufbau eines neuronalen Netzes}{section.2}% 5
\BOOKMARK [2][-]{subsection.2.3}{Berechnung des Ausgabevektors}{section.2}% 6
\BOOKMARK [2][-]{subsection.2.4}{Der Lernprozess}{section.2}% 7
\BOOKMARK [3][-]{subsubsection.2.4.1}{Backpropagation}{subsection.2.4}% 8
\BOOKMARK [3][-]{subsubsection.2.4.2}{Fehlerfunktionen}{subsection.2.4}% 9
\BOOKMARK [3][-]{subsubsection.2.4.3}{SGD}{subsection.2.4}% 10
\BOOKMARK [3][-]{subsubsection.2.4.4}{Zusammenfassung}{subsection.2.4}% 11
\BOOKMARK [2][-]{subsection.2.5}{Verschiedene Layerarten}{section.2}% 12
\BOOKMARK [3][-]{subsubsection.2.5.1}{Fully connected Layers}{subsection.2.5}% 13
\BOOKMARK [3][-]{subsubsection.2.5.2}{Convolutional Layers}{subsection.2.5}% 14
\BOOKMARK [3][-]{subsubsection.2.5.3}{Pooling Layers}{subsection.2.5}% 15
\BOOKMARK [1][-]{section.3}{PyTorch}{}% 16
\BOOKMARK [2][-]{subsection.3.1}{Datenvorbereitung}{section.3}% 17
\BOOKMARK [2][-]{subsection.3.2}{Definieren des Netzes}{section.3}% 18
\BOOKMARK [2][-]{subsection.3.3}{Trainieren des Netzes}{section.3}% 19
\BOOKMARK [1][-]{section.4}{Fallbeispiel I:Ein Klassifizierungsnetzwerk f\374r handgeschriebene Ziffern}{}% 20
\BOOKMARK [2][-]{subsection.4.1}{Aufgabe}{section.4}% 21
\BOOKMARK [2][-]{subsection.4.2}{Der MNIST Datensatz}{section.4}% 22
\BOOKMARK [2][-]{subsection.4.3}{Fragmentbasierte Erkennung}{section.4}% 23
\BOOKMARK [2][-]{subsection.4.4}{Ergebnis}{section.4}% 24
\BOOKMARK [1][-]{section.5}{Fallbeispiel II:Eine selbsttrainierende KI f\374r Tic-Tac-Toe}{}% 25
\BOOKMARK [2][-]{subsection.5.1}{Das Prinzip}{section.5}% 26
\BOOKMARK [2][-]{subsection.5.2}{Chance-Tree Optimierung}{section.5}% 27
\BOOKMARK [2][-]{subsection.5.3}{L\366sung mittels eines neuronalen Netzes}{section.5}% 28
\BOOKMARK [2][-]{subsection.5.4}{Vergleich}{section.5}% 29
\BOOKMARK [1][-]{section.6}{Schlusswort}{}% 30
\BOOKMARK [3][-]{subsubsection.2.4.1}{Fehlerfunktionen}{subsection.2.4}% 8
\BOOKMARK [3][-]{subsubsection.2.4.2}{Gradientenverfahren}{subsection.2.4}% 9
\BOOKMARK [2][-]{subsection.2.5}{Verschiedene Layerarten}{section.2}% 10
\BOOKMARK [3][-]{subsubsection.2.5.1}{Fully connected Layers}{subsection.2.5}% 11
\BOOKMARK [3][-]{subsubsection.2.5.2}{Convolutional Layers}{subsection.2.5}% 12
\BOOKMARK [3][-]{subsubsection.2.5.3}{Pooling Layers}{subsection.2.5}% 13
\BOOKMARK [1][-]{section.3}{PyTorch}{}% 14
\BOOKMARK [2][-]{subsection.3.1}{Datenvorbereitung}{section.3}% 15
\BOOKMARK [2][-]{subsection.3.2}{Definieren des Netzes}{section.3}% 16
\BOOKMARK [2][-]{subsection.3.3}{Trainieren des Netzes}{section.3}% 17
\BOOKMARK [1][-]{section.4}{Fallbeispiel I:Ein Klassifizierungsnetzwerk f\374r handgeschriebene Ziffern}{}% 18
\BOOKMARK [2][-]{subsection.4.1}{Aufgabe}{section.4}% 19
\BOOKMARK [2][-]{subsection.4.2}{Der MNIST Datensatz}{section.4}% 20
\BOOKMARK [2][-]{subsection.4.3}{Fragmentbasierte Erkennung}{section.4}% 21
\BOOKMARK [2][-]{subsection.4.4}{Ergebnis}{section.4}% 22
\BOOKMARK [1][-]{section.5}{Fallbeispiel II:Eine selbsttrainierende KI f\374r Tic-Tac-Toe}{}% 23
\BOOKMARK [2][-]{subsection.5.1}{Das Prinzip}{section.5}% 24
\BOOKMARK [2][-]{subsection.5.2}{Chance-Tree Optimierung}{section.5}% 25
\BOOKMARK [2][-]{subsection.5.3}{L\366sung mittels eines neuronalen Netzes}{section.5}% 26
\BOOKMARK [2][-]{subsection.5.4}{Vergleich}{section.5}% 27
\BOOKMARK [1][-]{section.6}{Schlusswort}{}% 28