Startseite       SB-Funktionen für Studierende    WiSe 2021/22      Switch to english language  Hilfe

Applied Machine Learning in Agriculture with R - Einzelansicht

  • Funktionen:

Grunddaten
Veranstaltungsart Vorlesung Kurztext
Veranstaltungsnummer 740858 SWS 4.00
Semester WiSe 2021/22 Studienjahr
Erwartete Teilnehmer/-innen 25 Hyperlink
Turnus jedes 2. Semester
Credits 6
Sprache englisch
Termine :
  Tag Zeit Turnus Termin Raum Lehrperson Status Bemerkung fällt aus am Max. Teilnehmer/-innen Module
Einzeltermine anzeigen -. 09:00 bis 16:00 Block 07.03.2022  bis
18.03.2022
   

Findet online statt!

 


Zugeordnete Person
Zugeordnete Person Zuständigkeit
Schmitt, Armin, Prof. Dr. verantwortlich
Prüfungen / Module
Modul Studiengänge
M.iPAB.0015.Mp: Applied Machine Learning in Agriculture with R
Modulbeschreibung
Master → Agrarwissenschaften →Master - Alle Schwerpunkte - Block D →M.iPAB.0015: Applied Machine Learning in Agriculture with R
Master → Integrated plant and animal breeding →Master - Block B - Wahlpflichtmodule I →M.iPAB.0015: Applied Machine Learning in Agriculture with R
Master → Integrated plant and animal breeding →Master - Block C - Wahlpflichtmodule II →M.iPAB.0015: Applied Machine Learning in Agriculture with R
Master → Integrated plant and animal breeding →Master - Double Degree - Block B - Elective compulsory modules →M.iPAB.0015: Applied Machine Learning in Agriculture with R
Master → Agrarwissenschaften →Master - Schwerpunkt Integrated Plant and Animal Breeding - Block B →M.iPAB.0015: Applied Machine Learning in Agriculture with R
Master → Agrarwissenschaften →Master - Schwerpunkt Nutztierwissenschaften - Block B →M.iPAB.0015: Applied Machine Learning in Agriculture with R
Master → Angewandte Informatik →Master - SP Anw. Syst.entwickl. - MP Grundlagen der Bioinformatik - Gr.1 →M.iPAB.0015: Applied Machine Learning in Agriculture with R
Master → Angewandte Informatik →Master - SP Anw. Syst.entwickl. - Vertiefung Bioinformatik - Bioinformatik →M.iPAB.0015: Applied Machine Learning in Agriculture with R
Master → Angewandte Informatik →Master - SP Bioinformatik - Bioinformatik - Gr.2 →M.iPAB.0015: Applied Machine Learning in Agriculture with R

Weitere Informationen zu den Prüfungsordnungen und Modulverzeichnissen finden Sie hier: Studienfächer von A-Z
Zuordnung zu Einrichtungen
Züchtungsinformatik
Inhalt
Voraussetzungen

Recommended previous knowledge: Basic
knowledge of R

Kommentar

Contents:
The course consists of lectures, exercises and project work.
After the lectures and the exercises the students will have to carry out a project work
that must be finished within eight weeks after the end of the lectures. The students as
well as the other research groups are welcome to suggest topics, possibly questions
related to their master thesis can be treated. The project work should be a concise
written report of about ten pages in which one or several of the techniques that were
treated in the course are applied

Modern agricultural research involves more and more the analysis of large datasets
comprising mesaurements of several variables. This module aims to teach interested
students fundamental analysis skills that permit them to cope with such data sets. In
more detail, the techniques that will be treated include:
• clustering
• artificial neural networks
• support vector machine
• decision trees
• random forests
• feature selection
Involved mathematical formalism will be avoided. The focus is rather on:
• gaining an intuitive understanding of the techniques
• to develop an understanding about which type of problem can be treated with
which technique
• the application of the techniques using machine learning-functions under R
• the graphical visualisation of the results
• and the interpretation of the results
The teaching will be based on the analysis of published real data sets from agricultural
research projects as far as possible.

Examination requirements:
• Knowledge about the analysis of big-data sets with the statistical package R and
interpretation of the results.
• Knowledge about different clustering algorithms
• Analysis of real agricultural data sets by applying different machine learning-
functions under R
• Knowledge about feature selection approaches

Leistungsnachweis

 Oral examination (approx. 20 minutes, 60%) and term paper (max. 10
pages, 40%)


Strukturbaum

Die Veranstaltung wurde 2 mal im Vorlesungsverzeichnis WiSe 2021/22 gefunden: