Zur Seitennavigation oder mit Tastenkombination für den accesskey-Taste und Taste 1 
Zum Seiteninhalt oder mit Tastenkombination für den accesskey und Taste 2 
Switch to english language
Startseite    Anmelden     
Logout in [min] [minutetext]
WiSe 2019/20

Machine Learning for Software Engineering - Einzelansicht

  • Funktionen:
Grunddaten
Veranstaltungsart Vorlesung SWS 3
Veranstaltungsnummer 417130002 Max. Teilnehmer/-innen
Semester SoSe 2017 Zugeordnetes Modul
Erwartete Teilnehmer/-innen
Rhythmus jedes 2. Semester
Hyperlink  
Weitere Links https://www.uni-weimar.de/de/medien/professuren/intelligente-softwaresysteme/
Sprache englisch
Termine Gruppe: [unbenannt]
  Tag Zeit Rhythmus Dauer Raum Raum-
plan
Lehrperson Bemerkung fällt aus am Max. Teilnehmer/-innen
Einzeltermine anzeigen
Mo. 09:15 bis 10:45 wöch. von 10.04.2017  Karl-Haußknecht-Straße 7 - Hörsaal (IT-AP)  

Übung

 
Einzeltermine anzeigen
Di. 11:00 bis 12:30 wöch. von 04.04.2017  Bauhausstraße 11 - Seminarraum 014  

Vorlesung

 
Einzeltermine anzeigen
Di. 11:00 bis 13:00 Einzel am 25.07.2017 Karl-Haußknecht-Straße 7 - Hörsaal (IT-AP)  

Klausur

 
Gruppe [unbenannt]:
 
 


Zugeordnete Person
Zugeordnete Person Zuständigkeit
Siegmund, Norbert, Prof., Dr.-Ing.
Studiengänge
Abschluss Studiengang Semester Leistungspunkte
Master Medieninformatik (M.Sc.), PV 29 - 4,5
Master Human-Computer Interaction (M.Sc.), PV15 - 4,5
Master Human-Computer Interaction (M.Sc.), PV14 - 4,5
Master Computer Science and Media (M.Sc.), PV 11 - 4,5
Zuordnung zu Einrichtungen
Intelligente Softwaresysteme
Medieninformatik
Inhalt
Beschreibung

Machine Learning for Software Engineering is about learning and optimizing complex tasks that are computationally intractable for exact methods. The goal of this course is to understand the principles of meta-heuristics in optimization as well as key concepts of learning based on neural nets.

 

Students should understand the following techniques and theories:

  • Problem space exploration and search-based optimization
  • Meta-heuristics for optimization
  • Relationship between biological learning and optimization with algorithms
  • Neural nets and deep learning

 

Students should be able to apply the above theories for solving concrete learning and optimization problems. Furthermore, they should appreciate the limits and constraints of the individual methods above.

 

Students should be able formalize and generalize their own solutions using the above concepts and implement them in a specified language (preferable in Python).

 

Students should master concepts and approaches such as

  • Simulated annealing
  • Swarm optimization
  • Ant colonization
  • Evolutionary algorithms
  • Sampling and Experimental Designs
  • Dimensionality Reduction
  • Neural nets
  • Deep learning

 

in order to tackle problems learning and optimizing huge problems, which are inherent to Digital Media. They should also be able to implement the algorithms and techniques in Python and be able to understand a proposed problem, to compare different approaches and techniques regarding applicability and accuracy, to make well-informed decisions about the preferred solution and, if necessary, to find their own solutions.

 

Students should develop an understanding of the current state of research in optimization and learning. With appropriate supervision, students should be able to tackle new research problems, especially in the area of search-based software engineering.

engl. Beschreibung/ Kurzkommentar

Machine Learning for Software Engineering

Machine Learning for Software Engineering is about learning and optimizing complex tasks that are computationally intractable for exact methods. The goal of this course is to understand the principles of meta-heuristics in optimization as well as key concepts of learning based on neural nets.

 

Students should understand the following techniques and theories:

  • Problem space exploration and search-based optimization
  • Meta-heuristics for optimization
  • Relationship between biological learning and optimization with algorithms
  • Neural nets and deep learning

 

Students should be able to apply the above theories for solving concrete learning and optimization problems. Furthermore, they should appreciate the limits and constraints of the individual methods above.

 

Students should be able formalize and generalize their own solutions using the above concepts and implement them in a specified language (preferable in Python).

 

Students should master concepts and approaches such as

  • Simulated annealing
  • Swarm optimization
  • Ant colonization
  • Evolutionary algorithms
  • Sampling and Experimental Designs
  • Dimensionality Reduction
  • Neural nets
  • Deep learning

 

in order to tackle problems learning and optimizing huge problems, which are inherent to Digital Media. They should also be able to implement the algorithms and techniques in Python and be able to understand a proposed problem, to compare different approaches and techniques regarding applicability and accuracy, to make well-informed decisions about the preferred solution and, if necessary, to find their own solutions.

 

Students should develop an understanding of the current state of research in optimization and learning. With appropriate supervision, students should be able to tackle new research problems, especially in the area of search-based software engineering.

Literatur

Handbook of Metaheuristics, Fred W. Glover, Gary A. Kochenberger, Springer Science & Business Media, 2006.

Machine Learning, Tom Mitchell, McGraw-Hill Education, 1997.

Essentials of Metaheuristics, Sean Luke, 2013.

A Field Guide to Genetic Programming, Riccardo Poli, William B. Langdon, Nicholas Freitag McPhee, Lulu Pr, 2008.

Make Your Own Neural Network, Rashid, Tariq, CreateSpace Independent Publishing Platform, 2016.

http://neuralnetworksanddeeplearning.com/index.html (online book)

Leistungsnachweis

Written or oral examination. Participation requires the successful completion of the course labs.

Zielgruppe

Computer Science and Media / Human-Computer Interaction


Strukturbaum
Keine Einordnung ins Vorlesungsverzeichnis vorhanden. Veranstaltung ist aus dem Semester SoSe 2017 , Aktuelles Semester: WiSe 2019/20

BISON-Portal Startseite   Zurück Kontakt/Impressum Datenschutz