|
Vorlesungsverzeichnis >> Fakultät Wirtschaftsinformatik und Angewandte Informatik >> Bachelor-/Masterstudiengänge Angewandte Informatik, Computing in the Humanities, International Information Systems Management, Software Systems Science, International Software Systems Science, Wirtschaftsinformatik, Wirtschaftspädagogik mit Schwerpunkt Wirtschaftsinformatik >>
|
Lehrveranstaltungen für Master
Angewandte Informatik
Kognitive Systeme
|
V KogSys-ML-B: Einführung in Maschinelles Lernen -
- Dozent/in:
- Ute Schmid
- Angaben:
- Vorlesung, 2 SWS, ECTS: 6
- Termine:
- Di, 8:00 - 10:00, WE5/00.019
- Voraussetzungen / Organisatorisches:
- Vorleistungen: GdI-MfI-B, MI-AuD-B
- Inhalt:
- Die Veranstaltung vermittelt vertieftes Wissen und Kompetenzen im Bereich Maschinelles Lernen mit dem Fokus auf symbolischen, neuronalen und statistischen Algorithmen. Anmerkung: Die Folien sowie weitere Materialien sind überwiegend in englischer Sprache. Vorlesung: In der Vorlesung werden wesentliche symbolische, statistische und neuronale Ansätze des maschinellen Lernens mit Bezügen zum menschlichen Lernen vertiefend eingeführt. Wesentliche Themengebiete sind: Entscheidungsbaumalgorithmen, Multilayer Perzeptrons, Instance-based Learning, Induktive Logische Programmierung, Genetische Algorithmen, Bayes'sches Lernen, Lerntheorie, Induktive Programmsynthese, Reinforcement Learning. Übung: Vertiefung von in der Vorlesung eingeführten Methoden und Techniken, zum Teil mit Programmieraufgaben in Java und PROLOG.
- Empfohlene Literatur:
- Mitchell, Machine Learning
|
Informationsvisualisierung
|
VIS-IVVA-M: Advanced Information Visualization and Visual Analytics -
- Dozent/in:
- Fabian Beck
- Angaben:
- Vorlesung, 2,00 SWS, ECTS: 6, Modulstudium
- Termine:
- Mo, 12:00 - 14:00, WE5/01.004
- Voraussetzungen / Organisatorisches:
- Recommended previous knowledge: Basic knowledge in information visualization and programming; knowledge in algorithms and data structures, human-computer-interaction, and machine learning and data science can be beneficial.
Note: This lecture is not directly based on the bachelor lecture VIS-GIV-B. Previous knowledge in visualization is nevertheless helpful, but can also be acquired during the semester. In particular, the VIS-Plus course will offer helpful tutorials and summaries.
- Inhalt:
- The course discusses methods for interactive information visualization and systems for explorative visual analysis. Visualizations blend with algorithmic solutions and get adopted to domain-specific needs. Giving a research-oriented perspective, the design and evaluation of such methods is the focus of the course, as well as their practical and interdisciplinary application in various fields.
Learning goals and competences: The students recognize the possibilities and limitations of data visualization and are able to apply visualization methods to concrete application examples. They understand the foundations of visual perception and cognition as well as their implications for the visual representation of data. They have a sound overview of possibilities for the visual representation of abstract data and are able to adapt visualization techniques to new problems and justify design decisions. On a conceptual level, they are able to integrate visualization techniques with interaction techniques and algorithmic solutions and design visual analytics solutions. They can evaluate visualization techniques in quantitative and qualitative user studies.
The workload for this module typically is as follows:
- Lecture and exercise sessions: 45h
- Preparation and review of the lecture: 30h
- Work on exercises and assignments: 75h
- Preparation for the exam: 30h
|
|
VIS-Proj-M: Masterprojekt Informationsvisualisierung - Visualizing Commits in Software Repositories -
- Dozentinnen/Dozenten:
- Cedric Krause, Fabian Beck
- Angaben:
- Projekt, 4,00 SWS, ECTS: 6
- Termine:
- Fr, 8:00 - 12:00, WE5/05.003
- Voraussetzungen / Organisatorisches:
- Requirements: Advanced programming skills.
Beneficiaries: Basic knowledge in visualization, human-computer-interaction, or machine learning and data science can be beneficial.
Registration: This course takes part in the central registration: https://vc.uni-bamberg.de/course/view.php?id=24052
- Inhalt:
- Focus Topic in Winter 2022/2023: Visualizing Commits in Software Repositories
Software projects are usually organized in repositories that are hosted either publicly (e.g., GitHub) or on a private server. These repositories contain all changes made to the source code in a series of commits, each of which has many properties that are either explicit (e.g., the author of the changes) or implicit (e.g., lines of code changed). The commits can be viewed as an event sequence in which each event is one single commit. In git-based repositories, there are also branches and merges, making the sequence richer and more complex. In this project group we aim at creating visualizations that describe the evolution of software projects with a focus on multivariate attributes of the events (commits). We will collect the commits of software projects and determine a variety of attributes for each of them and create a visual design that is flexible enough to represent different perspectives on the data (e.g., socio-technical, relationships to issues, code quality, etc.). Finally, we will implement a prototype of the visual design by leveraging visualization libraries either in Python (e.g., matplotlib, plotly) or in JavaScript (e.g., D3js).
General information:
In the project, students explore and apply different state-of-the-art approaches of applied computer science as a practical exercise. For a given scenario, an advanced interactive visualization application is to be developed in a group effort.
Learning goals and competences:
Students learn to work independently on a research-oriented problem and to coordinate this with group members. They design an interactive application that meets the requirements of a given scenario, while understanding the possibilities offered by visual and algorithmic methods. They implement a software system as a team, recognize the challenges of such collaboration, and jointly find solutions.
|
|
VIS-Sem-M: Masterseminar Informationsvisualisierung - Text and Visualization -
- Dozentinnen/Dozenten:
- Fabian Beck, Shahid Latif
- Angaben:
- Seminar, 2,00 SWS, ECTS: 3, first session on Oct 19 will be held remotely (see VC)
- Termine:
- Mi, 12:00 - 14:00, WE5/02.005
vom 11.1.2023 bis zum 8.2.2023
- Voraussetzungen / Organisatorisches:
- Requirments: None.
Beneficiaries: Basic knowledge in visualization, human-computer-interaction, or machine learning and data science can be beneficial.
Registration: This course takes part in the central registration: https://vc.uni-bamberg.de/course/view.php?id=24052
- Inhalt:
- Focus Topic in Winter 2022/2023: Text and Visualization
While a visualization is worth a thousand words, also the importance of words inside visualizations cannot be neglected. Text and visualizations act as complementary representations. For instance, visualization allows seeing patterns in large textual corpora. However, often, visualizations are complex, and text can play a role in unwinding this complexity in many ways. Similarly, to further ease up the interactions with a data visualization, natural language interfaces (e.g., chatbots) are being adopted. In this seminar, we will take a deeper look at the state-of-the-art research happening in regard to the relationship between text and visualization.
General information:
The seminar investigates current trends in a subarea of visualization research. Based on an extensive literature review, different visualization approaches will be compared and evaluated. All participants work on individually assigned topics that contribute different facets to an overarching seminar topic.
Learning goals and competences:
Students learn to independently research and find the latest research results regarding a given research topic in applied computer science. They discuss and evaluate state-of-the-art research results and develop a deep understanding of the individual topic, its potential use and application as well as limitations. They practice methods of scientific communication in oral and written form.
|
Erklärbares maschinelles Lernen
|
xAI-Sem-M1: Masterseminar Erklärbares Maschinelles Lernen [xAI-sem-M1] -
- Dozent/in:
- Christian Ledig
- Angaben:
- Seminar, 2 SWS, benoteter Schein, ECTS: 3
- Termine:
- Wir streben an, diese Veranstaltung in Präsenz durchzuführen. First meeting October 20, 4pm ct, WE5/05.003 // Second meeting October 24, 2pm ct, WE5/02.005
- Voraussetzungen / Organisatorisches:
- Interest and registration
If you have questions or want to express interest, please send an Email with name and matriculation number to christian.ledig@uni-bamberg.de. Registration via central VC course
Requirements:
completed course "Lernende System / Machine Learning" or "Einführung in die KI / Introduction into AI"
- Inhalt:
- This is a joint seminar between Prof. Kainz (FAU Erlangen-Nuremberg) and Prof. Ledig (University of Bamberg). The seminar will take place at Bamberg ERBA Campus and FAU Campus. Initial topic selection will take place in a hybrid format in Bamberg/Erlangen (in person on each site). Final topic presentations will take place in two sessions, one in person in Bamberg, one in person in Erlangen.
Topic: Human-in-the-Loop Machine Learning w/ focus on Healthcare
Motivation: Human-in-the-Loop Machine Learning describes processes in which humans and Machine Learning algorithms interact to solve one or more of the following: Making Machine Learning more accurate Getting Machine Learning to the desired accuracy faster Making humans more accurate Making humans more efficient Aim of this seminar is to give students insights about state-of-the-art Active Learning and interactive data analysis methods. Students will independently explore specific topics, which are then presented and discussed in class. Several potential topics will be provided but students are also encouraged to propose their own topics (after discussion with course lead).
Topics covered will include but are not limited to:
Introduction to Human-in-the-Loop Machine Learning: Active Learning Strategies, Uncertainty Sampling, Diversity Sampling, Other Strategies
Annotating Data for Machine Learning: Who are the right people to annotate your data?, Quality control for data annotation, User interfaces for data annotation
Transfer Learning and Pre-Trained Models: What are Embeddings?, What is Transfer Learning?
Adaptive Learning: Machine-Learning for aiding human annotation, Advanced Human-in-the-Loop Machine Learning
Goals
In-depth knowledge of aspects of human-in-the-loop machine learning, including deeper insight into current research. A capability to work independently on application-driven projects. To use a holistic view to critically, independently and creatively identify, formulate and deal with complex issues. To create, analyse and critically evaluate different technical/architectural solutions. To integrate knowledge critically and systematically. To clearly present and discuss the conclusions as well as the knowledge and arguments that form the basis for these findings in written and spoken English. A consciousness of the ethical aspects of research and development work.
The focus of the seminar will be biased towards approaches based on computer vision algorithms and medical image processing.
Format
The presentations for this seminar will be conducted as block seminar. Dates of final presentationsTBD.
We will meet in the beginning of the semester to discuss possible work areas and assign concrete topics to each participant. You will be provided pointers to literature and then independently familiarize yourself with the assigned topic. You will:
- present your topic as a 20 minute presentation (+5 min questions) and
- submit a written report of approximately 8 pages.
- The goal is to run the seminar in English including presentations and the written report.
The presentations will be conducted as a block seminar towards the end of the semester.
The weekly hours mentioned in the module description are an optional time slot to get support, guidance and feedback on your topic (as required).
Expected workload & Grading
The time (work load) of this module is expected to be roughly as follows:
- Attendance of seminar / presentation: 20h
- Literature review and familiarization with topic: 25h
- Preparation of presentation: 15h
- Written report: 30h
The grade will be determined in equal parts based on the presentation and report. Attendance of the presentations is mandatory.
|
Sprachgenerierung und Dialogsysteme
|
Projekt Dialogsysteme -
- Dozent/in:
- Stefan Ultes
- Angaben:
- Übung, 4 SWS, Schein, ECTS: 6
- Termine:
- Mo, 10:00 - 12:00, WE5/02.005
Mi, 14:00 - 16:00, WE5/02.005
The first meeting will be on Wednesday, 19 Oct 2022
- Voraussetzungen / Organisatorisches:
- Prior knowledge: knowledge in object-oriented programming (Python); knowledge in dialogue systems or related fields or scientific writing and LaTeX favorable
Typical work load:
- Meetings and talks: ~ 30h
- Familiarization with the project: ~ 30h
- Implementation: ~ 90h
- Preparation of presentation: ~ 30h
Language: English/German (course language as requested, submissions as individually preferred)
- Inhalt:
- The project provides the opportunity to work in groups of 4-5 students in a hands-on fashion. The goal is to understand and implement the different modules of a spoken dialogue system. We will focus on the basic functionality of each module and how to implement it in an industry-like development process. You will gain theoretical knowledge about the dialogue system modules as well as practical knowledge by implementing these modules using a ticket-based development flow. For the implementation, you are expected use Python. Other libraries are free to choose. At the end of the semester, you will present your results and hand in a technical project report.
The learning goals for this course are the following: the participants
- learn to familiarise themselves individually with the practical aspects of dialogue systems and to share these with their group members,
- are able to implement parts of a dialogue system to realize a given use-case scenario,
- understand, how the dialogue system modules operate and inter-operate with each other
- are able to realize a challenging implementation task as a team using industry-like development flows, identify challenges that arise from such a way working and jointly find solutions.
|
|
Vorlesung Dialogsysteme -
- Dozent/in:
- Stefan Ultes
- Angaben:
- Vorlesung, 2 SWS, benoteter Schein, ECTS: 3
- Termine:
- Mi, 12:00 - 14:00, WE5/01.006
Einzeltermin am 4.11.2022, Einzeltermin am 11.11.2022, Einzeltermin am 18.11.2022, Einzeltermin am 25.11.2022, 14:00 - 17:00, Online-Meeting
Erster Termin am 26.10.2022. In den Wochen vom 31. Oktober bis 25. November fällt die Präsenzveranstaltung am Mittwoch aus. Statt dessen findet jeweils Freitags ein Online-Termin statt.
ab 26.10.2022
- Voraussetzungen / Organisatorisches:
- Vorkenntnisse: Einführung in die KI bestanden
Die Arbeitsumfänge gestalten sich typischerweise wie folgt:
- Vorlesung: ~ 30h
- Vor- und Nachbereitung der Vorlesung: ~ 30h
- Prüfungsvorbereitung: ~30h
Sprache: Deutsch
- Inhalt:
- Diese Veranstaltung befasst sich mit Dialog als sprachlichem Verhalten und seiner Modellierung in technischen Systemen befassen. Sie führt in das Gebiet der Sprachdialogtechnologie ein und beinhaltet die gesamten Verarbeitungskette eines Dialogsystems: akustische Signalverarbeitung, Spracherkennung, natürliches Sprachverstehen, Dialogmanagement, Sprachgenerierung und Sprachsynthese. Industrieunternehmen, die im Bereich der Sprachdialogsysteme arbeiten, werden an einzelnen Terminen Gastvorlesungen halten.
Nach erfolgreicher Teilnahme an dem Kurs sollten Sie folgende Kenntnisse erworben haben:
- Allgemeines theoretisches Verständnis der Sprachdialogtechnologie
- Verständnis von Dialogmodellierung und der üblichen Modularisierung dieser Aufgabe
- Überblick über den aktuellen Stand der Technik für die sprachtechnologisch Anwendung Dialogsystem
- Kenntnis der Grundlagen der einzelnen Themengebiete eines modularen Dialogsystems
|
Informatik
Privatsphäre und Sicherheit
Softwaretechnik und Programmiersprachen
Wirtschaftsinformatik
Industrielle Informationssysteme
|
IIS-Sem-M: Masterseminar zu Industriellen Informationssystemen -
- Dozent/in:
- Sven Overhage
- Angaben:
- Seminar, 2,00 SWS
- Termine:
- Do, 14:00 - 16:00, WE5/02.020
Einzeltermin am 23.1.2023, 12:00 - 20:00, WE5/03.004
- Voraussetzungen / Organisatorisches:
- Die Einführungsveranstaltung findet am 20.10.2022 von 14-16 Uhr im Raum WE5/02.020 statt, ebenso die Einführung in das wissenschaftliche Arbeiten am 27.10.2022 von 14-16 Uhr. Zusätzlich wird es am 17.11.2022 von 14-16 Uhr noch eine weitere Veranstaltung geben. Das Seminar wird als Blockveranstaltung abgehalten. Dazu finden die Präsentationen für das Masterseminar am 23.01.2023 statt. Die Abgabe der Seminararbeiten erfolgt bis zum Freitag, den 17.02.2023.
Eine verbindliche Anmeldung ist vom 06.10.2022 (12 Uhr) bis 13.10.2022 (12 Uhr) über FlexNow möglich. Die Teilnehmeranzahl für das Seminar ist beschränkt. Bei Überbelegung erfolgt eine Zuteilung durch den Lehrstuhl. Sie erhalten bis Freitag, den 14.10.2022 (12 Uhr) eine Rückmeldung, ob Sie einen Seminarplatz erhalten haben.
- Inhalt:
- Master Seminar: Der Aufbau einer datengetriebenen Organisation - Anwendungspotentiale, Entwicklung und Herausforderungen bei der Implementierung
- Schlagwörter:
- WI-Seminar, WI-Seminare
|
Informationssystemmanagement
|
![](/img/anew/void.gif) |
![](/img/anew/void.gif) |
|
UnivIS ist ein Produkt der Config eG, Buckenhof |
|
|