64-113 From Data to Knowledge: AI-based Scientific Workflows for Knowledge Generation

Course offering details

Instructors: Dr. Manfred Eppe

Event type: General Professional Skills courses

Displayed in timetable as: MKKI-basiert Proz

Hours per week: 2

Language of instruction: German

Min. | Max. participants: - | 31

Registration group: Anmeldegruppe Methodenkompetenz

Comments/contents:
How can we draw conclusions and test hypotheses from the ever-increasing amounts of data generated by scientific experiments? How can these data be visualized and analyzed? Which tools are useful for this and how can one use them? 

This course addresses these questions and deals with modern AI-based methods of data science. Students will learn to use the Python programming language and data science libraries to formulate hypotheses and to verify or falsify them on the basis of collected data. In particular, artificial neural networks are used for classification, regression and grouping of data. 

Besides the practical aspects, a great deal of attention is paid to scientific work. What is a research question and how is it formulated? What is a research goal? How do you write a research paper, and how do you do it all as a team? These questions are dealt with in a mini-project. 

Although no formal attendance is required for the periods between the blocks, it is expected that students coordinate themselves independently in their teams to work intensively on the mini-projects during the block breaks.

Prior knowledge of Python, statistics and other basics is advantageous but not required. More important is a personal enthusiasm for scientific work and artificial intelligence.

Learning objectives:
The seminar serves to convey the following competencies:

* Using and understanding AI-based data science tools
* Creating and formulating research questions and hypotheses
* Presenting and evaluating a complex topic in a comprehensible way in a paper
* Presenting a complex topic in an understandable way with slides
* Scientific work in a team

In addition, the corresponding technical contents are to be learned within the scope of a mini-project. 

Didactic concept:
The event will be held digitally. There will be two teaching blocks on weekends and a final presentation for mini-projects. The blocks will be realized with Zoom and learning videos via Lecture2Go. More information will be made available approximately two weeks before the start of the first block. It is generally necessary that the students are virtually/digitally present during the block times.

The first block (14./15.11. 2020) will deal with classical methods of data science. Thereafter, the students will start generating preliminary results for their mini-projects. In the second block (10.1. 2021) neural networks will be used and the previous results will be compared with the results of the neural networks. The different methods can generate different results for the same research question. This trains the students to discuss the methods and to draw conclusions about the different results. This concluding discussion will be presented during the third block (31.1. 2021). 

 

Literature:
Ge´ron, A. (2017). Hands-on machine learning with Scikit-Learn and TensorFlow: concepts, tools, and techniques to build intelligent systems. O’Reilly Media.
VanderPlas, J. (2016). Python Data Science Handbook: essential tools for working with data. O’Reilly Media. 

?www.kaggle.com

Additional examination information:
Intensive work will be expected during the block breaks. The grade will be based on the final presentation and report. 

Appointments
Date From To Room Instructors
1 Sat, 21. Nov. 2020 10:00 18:00 Digital Dr. Manfred Eppe
2 Sun, 22. Nov. 2020 10:00 18:00 Digital Dr. Manfred Eppe
3 Sat, 9. Jan. 2021 10:00 18:00 Digital Dr. Manfred Eppe
4 Sat, 30. Jan. 2021 10:00 18:00 Digital Dr. Manfred Eppe
Exams in context of modules
Module (start semester)/ Course Requirement combination Exam Date Instructors Compulsory pass
InfB-MK Methodological Competence (SuSe 19) / InfB_MK  From Data to Knowledge: AI-based Scientific Workflows for Knowledge Generation Block exam 4  Block exam Time tbd Dr. Manfred Eppe; Prof. Dr. Stefan Wermter Yes
InfB-MK Methodological Competence (SuSe 20) / InfB_MK  From Data to Knowledge: AI-based Scientific Workflows for Knowledge Generation Block exam 2  Block exam Time tbd Dr. Manfred Eppe; Prof. Dr. Stefan Wermter Yes
InfB-MK Methodological Competence (WiSe 19/20) / InfB_MK  From Data to Knowledge: AI-based Scientific Workflows for Knowledge Generation Block exam 3  Block exam Time tbd Dr. Manfred Eppe; Prof. Dr. Stefan Wermter Yes
InfB-MK Methodological Competence (WiSe 20/21) / InfB_MK  From Data to Knowledge: AI-based Scientific Workflows for Knowledge Generation Block exam 1  Block exam Time tbd Dr. Manfred Eppe; Prof. Dr. Stefan Wermter Yes
InfB-MK Methodological Competence (WiSe 18/19) / InfB_MK  From Data to Knowledge: AI-based Scientific Workflows for Knowledge Generation Block exam 5  Block exam Time tbd Dr. Manfred Eppe; Prof. Dr. Stefan Wermter Yes
Class session overview
  • 1
  • 2
  • 3
  • 4
Instructors
Dr. Manfred Eppe