Students know different AI frameworks used in industry and research.
They are familiar with cloud services and know how to operate them efficiently.
They know about the advantages and disadvantages of the individual frameworks and their differences and interrelationships.
They are able to use these platforms in a data science project and modell, evaluate and optimize their parameters.
Students are able to define requirements and develop a concept for a selected project.

none

The module covers the following topics/contents:

• Application and configuration of popular AI frameworks, such as TensorFlow, Keras, PyTorch, Caffe or Julia etc.
• Application and configuration of popular cloud services, such as Google Colab, Amazon Cloud Services or IMB Watson etc.

• Project setup, planning & management
• Define requirements

Lecture script as provided in the course (required)
Francois Chollet, Deep Learning with Python, Manning, 2nd ed. 2020
Eli Stevens, Luca Antiga, Deep Learning with PyTorch, Manning 2020
Abhishek Kumar Annamraju, Akash Deep Singh, Introduction to Deep Learning with Caffe2, Packt, 2020
Christopher Bourez, Deep Learning with Theano, Packt, 2017

Integrated course - teaching & discussion, demonstration, practical examples.
Apply theoretical and practical concepts from completed modules to develop a concept study with regular supervision by project tutors.

Immanent examination character: assignment reports and presentation of the final concept study (to be implemented in Project (II)).