700.610 (23S) Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems

Sommersemester 2023

Anmeldefrist abgelaufen.

Erster Termin der LV
28.04.2023 15:30 - 16:30 B12a.2.1.1 On Campus
... keine weiteren Termine bekannt

Überblick

Lehrende/r
LV-Titel englisch Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems
LV-Art Kurs (prüfungsimmanente LV )
LV-Modell Onlinelehrveranstaltung
Semesterstunde/n 2.0
ECTS-Anrechnungspunkte 3.0
Anmeldungen 5 (30 max.)
Organisationseinheit
Unterrichtssprache Englisch
LV-Beginn 28.04.2023
eLearning zum Moodle-Kurs

Zeit und Ort

Liste der Termine wird geladen...

LV-Beschreibung

Intendierte Lernergebnisse

Methods & Goals

The aim of FOML is to communicate the fundamental principles and classical

techniques of Machine Learning to students, wich is essential to understand

modern Deep Learning techniques.

Besides theoretical input in form of slides and tutorials, students will work on

basic Machine Learning problems i.e. produce code in Python. Beyond creating

and training the model, students will learn how to conduct a ML study from

beginning to end, from problem definition to containerization using Docker.

In view of tools, this course will make use of open-source software: Python,

Scikit-Learn, Keras and possibly also PyTorch.

Lehrmethodik inkl. Einsatz von eLearning-Tools

Methods & Goals

The aim of FOML is to communicate the fundamental principles and classical

techniques of Machine Learning to students, wich is essential to understand

modern Deep Learning techniques.

Besides theoretical input in form of slides and tutorials, students will work on

basic Machine Learning problems i.e. produce code in Python. Beyond creating

and training the model, students will learn how to conduct a ML study from

beginning to end, from problem definition to containerization using Docker.

In view of tools, this course will make use of open-source software: Python,

Scikit-Learn, Keras and possibly also PyTorch.

Inhalt/e

This course on fundamentals of machine learning - FOML - intends to

communicate the basics of classical Machine Learning theory to Math, IT, and

ICT students. Building on basic Math skills students had gained in high school,

FOML introduces students to the broad field, teaches basic principles and

classical ML techniques (SVM, Random Forest, etc.), which is essential to

understand state-of-the-art Deep Learning techniques. As showcases, this

course will deal with everyday Machine Learning problems of the Energy

Informatics research field such as forecasting of time series, detecting

anomalies in energy grids and clustering of consumers based on household

appliances.

It is intended to have FOML laid out as conventional "Kurs" with 2 SWS and

3ECTS, starting in Sommersemester 2023. Though the case studies will focus

on energy data, this course welcomes students of any technical background.

Modules

1. Introduction to Machine Learning

i. Basic Terms and Definitions

ii. Supervised vs. Unsupervised

iii. Bagging vs Boosting

iv. Overfitting vs Underfitting

2. Module on Regression and Classification

i. Linear Regression / Least Squares

ii. Support Vector Regression

iii. Naive Bayes

iv. k-Nearest Neighbours

v. Decision Tree

vi. Ensemble Methods

vii. Random Forest

3. Module on Clustering

i. Intro to unsupervised learning

ii. k-means

iii. Hierarchical clustering

iv. DBSCAN

4. Module on Features

i. Dimensionality Reduction

ii. Feature Engineering

iii. Model Selection

iv. Parameter tuning

v. Pre/Postprocessing

5. Module on Modern Technical Aspects

i. Containerization using Docker

ii. Deploying ML models on the cloud

iii. CI / CD life cycle

6. Outlook on modern Machine Learning

i. Intro to Neural Networks

ii. Brief Review of Deep Learning (LSTM, GRU, Transformer)

iii. Review of recent breakthroughs



Prüfungsinformationen

Im Fall von online durchgeführten Prüfungen sind die Standards zu beachten, die die technischen Geräte der Studierenden erfüllen müssen, um an diesen Prüfungen teilnehmen zu können.

Beurteilungsschema

Note Benotungsschema

Position im Curriculum

  • Besonderer Studienbereich Nachhaltigkeit (SKZ: 999, Version: 12W.1)
    • Fach: LV-Pool (Wahlfach)
      • Nachhaltigkeit ( 4.0h SE / 8.0 ECTS)
        • 700.610 Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems (2.0h KS / 3.0 ECTS)
  • 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)
        • 700.610 Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems (2.0h KS / 3.0 ECTS)
  • 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)
        • 700.610 Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems (2.0h KS / 3.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 22W.1)
    • Fach: Information and Communicatons Enginnering: Supplements (Wahlfach)
      • 1.3b Ausgewählte Lehrveranstaltungen (siehe Curriculum Seite 16) ( 0.0h VC, KS / 14.0 ECTS)
        • 700.610 Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems (2.0h KS / 3.0 ECTS)
  • 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)
        • 700.610 Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems (2.0h KS / 3.0 ECTS)
  • Erweiterungsstudium (UG §54a) Nachhaltige Entwicklung und Energie (NhEE) (ES) (SKZ: 011, Version: 20W.1)
    • Fach: Energiemanagement und -technik (Pflichtfach)
      • 2.1 Smart Grids ( 0.0h VC / 4.0 ECTS)
        • 700.610 Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems (2.0h KS / 3.0 ECTS)
  • Erweiterungsstudium (UG §54a) Nachhaltige Entwicklung und Energie (NhEE) (ES) (SKZ: 011, Version: 20W.1)
    • Fach: Gebundenes Wahlfach 2: Vertiefung zu Energiemanagement und -technik (Wahlfach)
      • 4.1 Lehrveranstaltungen aus Vertiefung zu Energiemanagement und -technik ( 0.0h XX / 4.0 ECTS)
        • 700.610 Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems (2.0h KS / 3.0 ECTS)
  • Erweiterungsstudium (UG §54a) Nachhaltige Entwicklung und Energie (NhEE) (ES) (SKZ: 011, Version: 20W.1)
    • Fach: Gebundenes Wahlfach 3: Spezialisierung in einem der Vertiefungsfächer (Wahlfach)
      • 5.1 Lehrveranstaltungen Spezialisierung in einem der Vertiefungsfächer ( 0.0h XX / 4.0 ECTS)
        • 700.610 Fundamentals of Machine Learning with application to Energy Informatics and Networked Systems (2.0h KS / 3.0 ECTS)

Gleichwertige Lehrveranstaltungen im Sinne der Prüfungsantrittszählung

Diese Lehrveranstaltung ist keiner Kette zugeordnet