Künstliche Intelligenz und Maschinelles Lernen in der Praxis

1. 00:00In this video we want to revisit the content of the week
2. 00:03and repeat one. To the beginning of the week
3. 00:08we met Jupiter notebooks and Google and co, this
4. 00:13We will continue to use laptops in the course to
5. 00:16show the practical examples and follow the
6. 00:19of the ECB. We also have the basics of Python
7. 00:24and various libraries.
8. 00:29This week we also have key terms and definitions
9. 00:32, such as the distinction between artificial
10. 00:37Intelligence and machine learning, the term data science
11. 00:41and in the different areas of machine learning.
12. 00:45Then we have the first practical project under way
13. 00:48taken as a matter of topic, it was about the house price forecast
14. 00:52California.
15. 00:55For this we have looked at several interesting visualizations.
16. 01:01As a model for the forecast we have this week the supervised
17. 01:04learning technology regression. Here again
18. 01:10the reference to the learning objectives this week. You should now
19. 01:14reclassify key terms and definitions
20. 01:17if there are any ambiguities, you can also
21. 01:21once in the basic course look up the videos again
22. 01:24or ask in the forum. They should also be a basic understanding
23. 01:30for the programming languages Pyothon, here is also
24. 01:35once to emphasize that it is not necessary everything in detail
25. 01:38or write your own code.
26. 01:42After this week, they should also be understood in broad terms
27. 01:45have how to implement house price forecasts and which
28. 01:49steps are necessary.
29. 01:54In the next week, we will devote ourselves to the application of a
30. 01:57Film proposal system. As an additional topic we will be covering topics of
31. 02:02handle data preparation. We look forward to seeing you in week two
32. 02:07again.

To enable the transcript, please select a language in the video player settings menu.