250047 VU Applied machine learning (2022W)
Continuous assessment of course work
Labels
ON-SITE
Registration/Deregistration
Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).
- Registration is open from Th 01.09.2022 00:00 to Sa 24.09.2022 23:59
- Deregistration possible until Mo 31.10.2022 23:59
Details
max. 50 participants
Language: German
Lecturers
Classes (iCal) - next class is marked with N
Vorbesprechung am 3. Oktober 16:45.
Monday
03.10.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
05.10.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
10.10.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
12.10.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
17.10.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
19.10.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
24.10.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
31.10.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
07.11.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
09.11.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
14.11.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
16.11.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
21.11.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
23.11.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
28.11.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
30.11.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
05.12.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
07.12.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
12.12.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
14.12.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
09.01.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
11.01.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
16.01.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
18.01.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
23.01.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Wednesday
25.01.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Monday
30.01.
16:45 - 18:15
Hörsaal 11 Oskar-Morgenstern-Platz 1 2.Stock
Information
Aims, contents and method of the course
Assessment and permitted materials
The grade results from the elaboration/tests and the team project.
Minimum requirements and assessment criteria
The course imparts basic knowledge about "Machine Learning" using lectures, exercises and a small team project.
Examination topics
Moodle test + presentation of team project in the end of semester
Reading list
Lecture notes.Further literature:
Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition. O'Reilly Media, 2019.
Forsyth, David, Applied Machine Learning. Springer International Publishing, 2019.
Shalev-Shwartz, Shai, and Shai Ben-David, Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.
Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition. O'Reilly Media, 2019.
Forsyth, David, Applied Machine Learning. Springer International Publishing, 2019.
Shalev-Shwartz, Shai, and Shai Ben-David, Understanding machine learning: From theory to algorithms. Cambridge university press, 2014.
Association in the course directory
ZWM
Last modified: Th 29.09.2022 16:49
The VU aims to "reconcile" theoretical and application-relevant aspects. In addition to the particularly practically relevant basics such as data analysis, model selection, validation, over- and underfitting, "feature selection", we will discuss "classical methods" such as non-linear model reduction (PCA, MDS, kernel methods, etc.), classification (logistic regression, random forests , SVMs, etc), regression (kernel rigde regression, lasso, etc), clustering, ensemble learning, as well as the basics of the current Deep Neural Networks (DNN), especially new advanced methodologies like autoencoders/-decoders, convolutional Neural Networks and " Physics-Informed Neural Networks (PINN)".Using practical exercises, the handling of this is taught "hands-on" via Python, scikit-learn and keras/tensor flow, where we use the no-setup environment Kaggle with free GPU access. The VU will also deal with current research topics and applications in physics and materials research.Structure:
The VU "Applied Machine Learning" combines (i) a "theory part" where mathematical and numerical basics of machine learning are presented, (ii) practical exercises that accompany the first part, and (iii) a "group work" where a small application problem in groups of about 2-6 people is considered and presented.