700.197 (24S) Tutorial Machine Learning and PyTorch Basics
Überblick
- Tutor/in/Innen
- LV-Titel englisch Tutorial Machine Learning and PyTorch Basics
- LV-Art Tutorium
- LV-Modell Onlinelehrveranstaltung
- Semesterstunde/n 2.0
- ECTS-Anrechnungspunkte 0.0
- Anmeldungen 12
- Organisationseinheit
- Unterrichtssprache Englisch
- mögliche Sprache/n der Leistungserbringung Englisch
- LV-Beginn 01.03.2024
- eLearning zum Moodle-Kurs
Zeit und Ort
LV-Beschreibung
Intendierte Lernergebnisse
This tutorial supports the beginners Machine Learning and Deep Learning who are enrolled in machine learning, or deep learning courses. It will introduce the students to basic Machine Learning techniques, Models, Frameworks and tools.
Lehrmethodik inkl. Einsatz von eLearning-Tools
In the BBB room with theory and programming examples.
Inhalt/e
The course will cover the following topics:
1- Introduction to Machine Learning:
- What is AI, Machine Learning, and Deep Learning ?
- Overview of Machine Learning: Definitions and significance.
- ML Techniques (Supervised, Unsupervised, Semi-Supervised Learning).
- Artificial Neural Networks Architectures
- Activation Functions, Loss Functions, Optimization
- Regression and Classification: Linear Regression, Logistic Regression, Decision Trees, Random Forest, Support Vector Machines.
- ML Pipeline: Data Collection, Preprocessing, Feature Engineering, Model Training, Evaluation.
- Introduction to CNN
- Introduction to GenAI (GAN, RNN, Transformer Models,...)
2- Practical Implementation:
- Most of the parts mentioned above will be implemented during the tutorial online through coding.
- Introduction to Pandas, Numpy.
- Introduction to Tensors using Tensorflow and PyTorch
- Introduction to Git and Github (Version Control)
- Interaction with different datasets (MNIST, Fashion MNIST, CIFAR10, HF opus_books,... etc)
- Final Project (Optional)
Parts of the mentioned above will be explained in parallel to review the theory and implement it in practice.
Erwartete Vorkenntnisse
- Basic-Intermediate Python Skills.
(Python basics can be covered during the tutorial depending on the knowledge of the students)
- Notice: Content can be adapted depending on the time-frame and previous knowledge of the enrolled students (Even If they have no knowledge), the tutorial is meant to support students who need help!
Curriculare Anmeldevoraussetzungen
none
Literatur
will be given
Prüfungsinformationen
Prüfungsmethode/n
This tutorial idoes not provide any grade, as no ECTS points can be earned, therefore there is no exam.
Prüfungsinhalt/e
none
Beurteilungskriterien/-maßstäbe
-
Beurteilungsschema
Note BenotungsschemaPosition im Curriculum
- Masterstudium Information and Communications Engineering (ICE)
(SKZ: 488, Version: 15W.1)
-
Fach: Information and Communications Engineering: Supplements (NC, ASR)
(Wahlfach)
-
Wahl aus dem LV-Katalog (Anhang 4) (
0.0h VK, VO, KU / 14.0 ECTS)
- 700.197 Tutorial Machine Learning and PyTorch Basics (2.0h TU / 0.0 ECTS)
-
Wahl aus dem LV-Katalog (Anhang 4) (
0.0h VK, VO, KU / 14.0 ECTS)
-
Fach: Information and Communications Engineering: Supplements (NC, ASR)
(Wahlfach)
- Masterstudium Information and Communications Engineering (ICE)
(SKZ: 488, Version: 15W.1)
-
Fach: Information and Communications Engineering: Supplements (NC, ASR)
(Wahlfach)
-
Wahl aus dem LV-Katalog (Anhang 4) (
0.0h VK, VO, KU / 14.0 ECTS)
- 700.197 Tutorial Machine Learning and PyTorch Basics (2.0h TU / 0.0 ECTS)
-
Wahl aus dem LV-Katalog (Anhang 4) (
0.0h VK, VO, KU / 14.0 ECTS)
-
Fach: Information and Communications Engineering: Supplements (NC, ASR)
(Wahlfach)
- Masterstudium Information and Communications Engineering (ICE)
(SKZ: 488, Version: 15W.1)
-
Fach: Free Electives
(Freifach)
-
Free Electives (
0.0h XX / 6.0 ECTS)
- 700.197 Tutorial Machine Learning and PyTorch Basics (2.0h TU / 0.0 ECTS)
-
Free Electives (
0.0h XX / 6.0 ECTS)
-
Fach: Free Electives
(Freifach)
- Masterstudium Information and Communications Engineering (ICE)
(SKZ: 488, Version: 22W.1)
-
Fach: ICE- Supplements
(Wahlfach)
-
2.3b Ausgewählte Lehrveranstaltungen (siehe Curriculum Seite 18) (
0.0h VC, KS / 14.0 ECTS)
- 700.197 Tutorial Machine Learning and PyTorch Basics (2.0h TU / 0.0 ECTS)
-
2.3b Ausgewählte Lehrveranstaltungen (siehe Curriculum Seite 18) (
0.0h VC, KS / 14.0 ECTS)
-
Fach: ICE- Supplements
(Wahlfach)