Research Group for Applied Software Engineering
Forschungsgruppe für Angewandte Softwaretechnik

Applications of Machine Learning in Software Engineering

Master Seminar (IN2107, IN8901)

Beschreibung

Thema des Seminars sind Ansätze aus den Bereichen Maschinelles Lernen und Data Mining und deren Einsatz in der Softwareentwicklung. Es wird diskutiert, wie solche Ansätze eingesetzt werden können, um Programme besser zu verstehen, große Mengen an Benutzerinput zu analysieren und wie Wissen und Zusammenhänge aus unstrukturierten Daten gewonnen werden kann.

Jeder Teilnehmer präsentiert dabei eine Ansatz des Maschinellen Lernens und eine Anwendung in der Software Entwicklung.

Summary

This seminar focuses on techniques from machine learning and data mining, and surveys their application in software engineering.
In particular, the seminar investigates how such techniques aid program comprehension, help to analyze and interpret large amounts of user input, and facilitate the extraction of relevant knowledge from unstructured data.

During the seminar each participant will present a machine learning technique including a particular application in software engineering.

Organizational Issues

  • NEW NEW NEW The kickoff meeting will be on 6.11, 14-15 h, room 01.07.58. We will discuss research methods and seminar topics in that session. NEW NEW NEW
  • Report and presentation can be in German or English.
  • For signing up in the seminar write an email to emitza.guzman(at)mytum.de.
  • In case of any questions please write an e-mail to  emitza.guzman(at)mytum.de.

 

Modalities

Grades will be based on the following criteria:

  • Ability to do independent research
  • Oral presentation
  • Written term paper
  • Active participation in all the other presentations (compulsory attendance)

Lecturers

Teaching Assistants

 

Topics

 

 

Paper

Conf.

ML Technique

Presenter

Advisor

Henß et al.:
Semi-automatically extracting FAQs to improve accessibility of software development knowledge

ICSE 2012

Latent Dirichlet Allocation

Aleksandar Stoimenov

Emitzá Guzmán

Bacchelli et al.:
Content classification of development emails                                                                                                           

ICSE 2012

Naive Bayes

Martin Stoll

Emitzá Guzmán

McMillan et al:
Detecting Similar Software Applications

ICSE 2012

Latent Semantic Indexing

Hao Ji

Emitzá Guzmán

Murphy-Hill et al.:
Improving Software Developers
Fluency by Recommending Development Environment Commands

FSE 2012

Collaborative Filtering

Burak Söhmelioglu

Emitzá Guzmán

Zhong et al.:
Inferring Resource Specifications from Natural Language API Documentation

ASE 2009

Hidden Markov Chains

Viktor Bogishef

Emitzá Guzmán

Kim et al.:
Towards an Intelligent Code Search Engine

AAAI 2010

K-means

Pei Li

Emitzá Guzmán

Di Fatta et al.:
Discriminative Pattern Mining in Software Fault Detection

SOQUA 2006

Frequent subtree mining

Mads Esholdt Wiemann

Tobias Röhm

Lo et al.:
Classification of Software Behaviors for Failure Detection: A Discriminative Pattern Mining Approach

KDD 2009

Frequent iterative pattern mining, classification

Vesko Georgiev

Tobias Röhm

Ghazarian, Noorhosseini:

Automatic detection of users' skill levels using high-frequency user interface events

User Modeling and User-Adapted Interaction, 2010

Decision Trees

Rui Yuan

Tobias Röhm

Tseng, Lin:

Efficient mining and prediction of user behavior patterns in mobile web systems

Information and Software Technology 2006

SPAM mine

(own algo)

Serge Krauze

Tobias Röhm

Saito et al.:

Understanding user behavior through summarization of window transition logs

Databases in Networked Information Systems, 2011

HMM (task summary)
PCA (comparison of users)

Zdravko Georgiev

Tobias Röhm

Romero et al.:
Design pattern mining enhanced by machine learning

ICSM, 2005

Machine Learning techniques

Mehdi Foudhaili

Tobias Röhm