Funktionen

Print[PRINT]
.  Home  .  Lehre  .  Seminare  .  Wintersemester 2021/22  .  Hauptseminar ML & AI

Hauptseminar:
Emerging Topics in Machine Learning and AI

Hauptseminar für Master-Studiengänge
im Wintersemester 2021 (LMU, TUM IN0014, IN4422)

Prof. Dr. D. Kranzlmüller
Dr. Andre Luckow
Dr. Karl Fuerlinger
Maximilian Höb

Welcome to the Master's Seminar on "Emerging Topics in Machine Learning and AI" in the winter term 2021/22. Here you will be able to find all the details concerning the seminar.

News

  • 22.01.2022: Seminar Papers
  • 17.01.2022: The block seminar will take place on Jan 29, 2022, 09:00-18:00 Uhr s.t. Due to the current situation it will be held online via Zoom. Passcode: 724059 (Please email advisor list in case of problems).
  • 23.12.2021:Peer Reviews available for download. Happy holidays!
  • 08.12.2021:Review Assignments and Papers online
  • 27.10.2021:The scientific work lecture will start at 6 c.t. (not s.t.) on Oct 27. Zoom: Link. Passcode: 724059 (Please email advisor list in case of problems).
  • 23.10.2021:Topic assignments can be downloaded here
  • 13.10.2021:The introduction lecture will take place on October 20th, 6pm CET s.t. via Zoom. Passcode: 724059 (Please email advisor list in case of problems).
  • 09.08.2021: Welcome to the website of the seminar "Emerging Topics in Machine Learning and AI" in the winter term 2021/22!

Inhalt des Seminars

Introduction

Machine Learning (ML) and Artificial Intelligence (AI) are transformational technologies that will have a significant impact on science and business. The aim of this seminar is to give the student an overview of the topics of data & compute infrastructures, machine learning and AI. The aim is to develop a technical understanding of large-scale systems and infrastructures for data infrastructures and advanced analytics. The students deepen their computer science knowledge in a practice-oriented way and with methods, techniques, procedures, tools and infrastructures for the processing and analysis of large data:

  • Machine Learning (Methods & Tools: Tensorflow and Pytorch)
  • Deep Learning: Convolutional Neural Networks (ResNet, Yolo, SSD)
  • Natural Language Processing: Word Embeddings, Language Models (RNNs, LSTMs, Transformers), Knowledge Graphs
  • Scalable Machine Learning: Distributed Training, AI Hardware
  • Quantum Machine Learning: Variational Algorithms, Optimization
  • Emerging Machine Learning Applications in Computer Systems, Cybersecurity and Fault Tolerance
  • Responsible AI: AI Ethics, Robust AI

Organization

Structure

The seminar will be based on the metaphor of a conference. Students will prepare a conference paper (technical report) on a chosen topic and will submit it to the seminar organizer (the fictitious program committee), receive an assessment of their submission from a supervisor and present (possibly corrected) paper at the fictitious conference at the end of the semester. After the first version of the paper has been submitted, each participant will be assigned two papers to review (according to a review given template, so that each paper will receive two reviews. This should increase the quality of the elaborations and familiarize the participants with the process of a scientific publication process. After the review, the authors have another 2 weeks to address the obtained comments/suggestions. Both the quality of the reviews and the implementation of the comments will be considered in the grading process.

The conference itself, in which all presentations are held, is designed as 1 to 2 day event at the end of the term. The exact date and the agenda will be announced on this website.

The introduction event for all seminar participants will take place in the first or second lecture week. Only in this event the topics are assigned. Participation in the introduction event is obligatory for all participants.

Important: Everyone who does not participate in the introduction event will lose his seminar seat due to the great demand!

In the course of the semester, mandatory lectures on scientific work, presentation techniques are planned. The Latex lecture is voluntary.

Please review the guidelines for the creation of scientific papers: Guidelines for seminar and scientific papers.

Formal Criteria

The final grade of the seminar is determined by the quality of the scientific paper, presentation, the contributed reviews, and participation in the seminars.

Paper:

The paper must meet the following criteria:

  • Use of the Latex Template IEEE(see Downloads)
  • Scope: minimum 6 to 8 pages
Non-conformance to one of the criteria will negatively impact the final grade!

Peer Review:

Participation in the review process is obligatory for the successful completion of the seminar! The quality of the review will be considered in the final grade.

Participation in the review process is obligatory for the successful existence of the seminar!

Vortrag:

The final presentation during the block seminar should not be longer than 20 minutes. It is planned to have a 5 minute Q&A session after each talk. Please use one of the suggested templates when prepairing your slide decks.

Participation in the complete block event is obligatory for all participants of the seminar!
The use of the wrong template will negatively impact the final grade.

NOTE: Once participation has been confirmed (i.e. a topic has been chosen and agreed to be presented with the supervisor) there will be no possibility to leave the event without the corresponding participation being considered as unsuccessful (i.e. student gets 5.0). No-show for the final presentation will also be considered as an unsuccessful participation.

Topics

You will find all availabe topics here: Seminar Topics

Online Rules

While LMU is closed, most teaching happens currently online. As teachers, we ask you to be forgiving if things should not work perfectly right away, and we hope for your constructive participation. In this situation, we would also like to explicitly point out some rules, which would be self-evident in real life:

  • In live meetings, we ask you to responsibly deal with audio (off by default) and bandwidth (video as needed).
  • Recording or redirecting streams by participants is not allowed.
  • Distributing content (video, audio, images, PDFs, etc.) in other channels than those foreseen by the author is not allowed.

If you violate one of these rules, you can expect to be expelled from the respective course, and we reserve the right for further action.

Timeline

Event Dates:

  • 20.10.2020, 18 Uhr s.t.: Introduction and Topic Assignment
  • 27.10.2020, 18 Uhr c.t.: Scientific Work und LaTeX Tutorial
  • 29.01.2022, 09:00-18:00 Uhr s.t. (confirmed): Block Seminar (a href=" https://lmu-munich.zoom.us/j/95660481810?pwd=VFd6MnAxK1E5V3hOc1dPY2NjL3dUZz09">Zoom Link. Passcode: 724059 (Please email advisor list in case of problems))

Important Dates:

  • 22.10.2021, 23:59 s.t.: Submission of the Topic Preferences
  • 24.10.2021, 23:59 s.t.: Topic Assignments
  • 03.11.2021, 23:59 s.t.: Submission of the Outline
  • 08.12.2021, 23:59 s.t.: Submission of Paper
  • 10.12.2021, 23:59 s.t.: Peer Review Assignements
  • 22.12.2021, 23:59 s.t.: Submission of Reviews
  • 19.01.2022, 23:59 s.t.: Submission of final paper
  • 26.01.2022, 11:59 s.t.: Submission of final presentation
All artifacts must be submitted to Uni2Work. In the case of a system error, please send your documents via e-mail to your supervisor and to the organizing team of the seminar: seminar-betreuer@nm.ifi.lmu.de

Contacts

Questions, criticism and suggestions are always welcome. Please use the seminar-specific e-mail address seminar-betreuer@nm.ifi.lmu.de.

Tipps zur Bearbeitung

Downloads

  1. LaTeX-Vorlage IEEEtran
  2. Notes on Paper Writing
  3. Review-Vorlage
  4. Peer Review Guidelines
  5. Slides Introduction
  6. Slides Scientific Work
  7. Slides Latex
  8. Topic Assigments
  9. Submissions
  10. Peer Review Assignments
  11. Peer Reviews
  12. Seminar Paper Collection
  13. Agenda for Seminar
  14. Presentations