Beste Grafikkarten GPUs: [[https://timdettmers.com/2019/04/03/which-gpu-for-deep-learning/]]

Machine Learning

Artificial Intelligence

Machine Learning Maschine Learning


Unterschiede Gehirn neuronales Netz 
https://www.golem.de/news/kuenstliche-intelligenz-wie-sich-deep-learning-vom-gehirn-unterscheidet-2202-162231-4.html


{{::neuronla_networks.jpg?400|}}

====== Neuronale Netzwerke ======
Einführung Videos (engl.): [[https://www.3blue1brown.com/neural-networks]]
Einführung (Kostenloses Buch, engl.): [[http://neuralnetworksanddeeplearning.com/]]


  * Parameter: Anzahl der Neuronen (Parameter: Bias/Addition) plus Anzahl der Verbindungen (Weight/Multiplikator) zwischen allen Neuronen
  * Aktivierungsfunktion: Funktion, welchen Wert das Neuron weitergibt. Oft ReLU (Rectified Linear Unit) =max(0, x) (nur positive Zahlen werden weitergegeben)
====== Fertig trainierte KI-Netzerke ======

===== Grafik =====
Videos online erstellen kostenlos: https://pikalabsai.org/
===== Text =====

[[https://www.golem.de/specials/gpt-3/|GPT-3]] : Nicht mehr frei seit 3 (am besten Trainiertes Netz, frei wäre angebl. zu gefährlich)

Frei:

[[https://www.eleuther.ai/projects/gpt-neo/|GPT-Neo]]

[[https://www.eleuther.ai/projects/gpt-neox/| GPT-NeoX]]
====== Deep Learning ======

Crash course Google : https://developers.google.com/machine-learning/crash-course/


Machine Learning

Software Links: [[http://deeplearning.net/software_links/]]


===== Torch =====


[[http://torch.ch/]]


===== OpenCV =====

==== Beispiele ====


=== Vorbeifahrende Autos zählen ===


Object tracking in video with OpenCV and Deep Learning ((https://youtu.be/19vaot75JCY))

Pattern: [[https://developer.ibm.com/patterns/detect-track-and-count-cars-in-a-video/]]

Repo: [[https://github.com/IBM/powerai-counting-cars]]


===== Frameworks =====




==== PyTorch ====

==== TensorFlow ====


[[https://www.statworx.com/de/blog/data-science/einfuehrung-tensorflow/|Sehr gute Einführung Deutsch]]

[[https://www.tensorflow.org/tutorials]]


==== Keras ====

Grundlagen: [[https://www.tensorflow.org/tutorials/keras/classification]]


==== DL4J ====


==== Caffee ====


==== Microsoft Recognition Toolkit ====

===== YOLO =====

You only look once

Quelle((https://www.youtube.com/watch?v=4eIBisqx9_g))


You Only Look Once - this object detection algorithm is currently the state of the art, outperforming R-CNN and it's variants. I'll go into some different object detection algorithm improvements over the years, then dive into YOLO theory and a programmatic implementation using Tensorflow!

Code for this video:
https://github.com/llSourcell/YOLO_Object_Detection

More learning resources:
https://pjreddie.com/darknet/yolo/

https://timebutt.github.io/static/how-to-train-yolov2-to-detect-custom-objects/

http://machinethink.net/blog/object-detection-with-yolo/

https://github.com/pjreddie/darknet/wiki/YOLO:-Real-Time-Object-Detection

https://github.com/KleinYuan/easy-yolo

https://medium.com/@xslittlegrass/almost-real-time-vehicle-detection-using-yolo-da0f016b43de

https://medium.com/diaryofawannapreneur/yolo-you-only-look-once-for-object-detection-explained-6f80ea7aaa1e