Hauptseminar Computational Aspects of Machine Learning - Winter 17

From Sccswiki
Revision as of 15:51, 20 November 2017 by August (talk | contribs) (→‎Schedule)
Jump to navigation Jump to search
Winter 17
Kilian Röhner, Moritz August
Time and Place
Wed. 10am till 12pm room MI 02.07.023 starting from 25. October (see schedule below)
Students from Bachelor {Informatics, Information Systems, Games Engineering} (IN0014), Master {Informatics, Games Engineering} (IN2107) and Master Computational Science and Engineering (IN2183)
Semesterwochenstunden / ECTS Credits
2 SWS / 4 Credits


  • Preliminary Meeting: July 5th 2017, 11am sharp, MI 02.07.023
  • Take a look at the Coursera Machine Learning course. If you are new to the field, the online course is a good way to get an overview.


Machine Learning is a rapidly growing area of research on the intersection of applied mathematics, informatics, and computational science. With advances in the machine learning theory and algorithms as well es with increasing amount of data and complexity of the models, development of fast, efficient and scalable algorithms increasingly gains importance. Hereby the range of applied techniques spreads from exploiting embarrassingly parallel tasks in a data-centric fashion to approximation methods with satisfying error limits.

In the seminar we are going to focus on the advanced methods for machine learning with particular interest in handling large-scale problems. While some topics would deal with the complete learning algorithms, others would focus on efficient solution of subtasks common for many different algorithms, e.g. nearest neighbors search or MCMC sampling.


Preliminary schedule of the presentations

Date Forename Surname Topic Advisor Chair Reviewer 1 Reviewer 2 Reviewer 3
25.10.17 Yoon Hee Ha Parallelization paradigms and parallel performance models Kilian Abhilasha Nikolaos Annie
08.11.17 Aamna Najmi Large scale graph mining Moritz
15.11.17 Maximilian Mozes Large scale Bayesian Inference Moritz Nikolaos Pei-Hsuan Yuriy Nikolaos
22.11.17 Yuanze Chen Black Box Variational Inference Moritz Pei-Hsuan Yoon Hee Annie
29.11.17 Abhilasha Mohania Online Learning Kilian Yoon Hee Annie Maximilian Nikolaos
06.12.17 Juanita Mendonca Real-time data mining with guaranteed throughput Kilian
13.12.17 Abraham Duplaa Large scale kernel learning Moritz
06.12.17 Nikolaos Ioannis Bountos Cloud-based machine learning Moritz Annie Yuriy Yuanze Maximilian
10.01.18 Pei-Hsuan Huang Data mining with sparse grids Kilian Yuriy Yoon Hee Abhilasha
17.01.18 Sarthak Gupta Large Scale Similarity Search Moritz
24.01.18 Annie Wachsmuth Manifold Learning Moritz Maximilian Yuanze Pei-Hsuan Yoon Hee
31.01.18 Yuriy Arabskyy Speeding-up deep learning training Moritz Yuanze Abhilasha Maximilian


We will cover the following topics in the seminar, also participants may suggest their own topics if those suit the goals of the seminar.

  • Parallelisation paradigms and parallel performance models
  • Large scale Bayesian inference
  • Large scale kernel learning
  • Speeding-up deep learning models
  • Speeding-up deep learning training
  • Resource-aware/constrained machine learning methods
  • Online learning
  • Real-time data mining with guaranteed throughput
  • Data mining with sparse grids
  • Large scale graph mining
  • Machine learning as a black box solution
  • Cloud-based machine learning
  • Manifold learning
  • ...


The seminar is intended for computer science bachelor students in advanced semesters and the master students with focus on computer science, computational science and engineering, or robotics and artificial intelligence.

If you want to participate, you are expected to have knowledge of fundamentals of applied mathematics, such as linear algebra, probability theory, calculus, and convex optimisation. As we will cover advanced topics, some general understanding of the basic concepts of machine learning is required.

Moreover, you should have programming experience in at least one programming language. Understanding of basic concepts of computational science is desirable, so if you know what SIMD, MISD, NUMA, MPI, GPGPU, and HDF5 mean, you are on the safe side.


If you feel like a data science unicorn we are looking for, please follow the instructions below and send us the information about your background and experience, 3 preferred topics (ranked) or your own topic suggestions.

To apply, do the following until July 19th:

  • Send an E-Mail to caml at mailsccs.in.tum.de containing
    • As subject: Application Computational Aspects of Machine Learning WS 17/18
    • Your Name
    • Three preferred topics (ranked), can include your own topic suggestions
    • Your study program and the semester you will be in in WS17/18
    • A short motivation containing your previous experience, why do you want to participate in the seminar, your expectations from the seminar etc.
  • Additionally, you are required to register for the seminar in the matching system.


Organisational Details

  • Weekly sessions. Day, time, and room tba.
  • Talk: 45 minutes + 15 minutes discussion
  • Extended abstract: 1 page article document class with motivation, key concepts and results
  • Paper: min. 5 pages max. 6 pages in IEEE format
  • Language: English
  • max. 12 Participants
  • Blind peer-review process
  • Session chairing


Dates to keep in mind:

  • July 14th till 19th: Application and registration in the matching system of the department
  • 28th of July: Notification of participants, topic discussions, etc.
  • Week starting with October 23th: first session, first talk.


  • 1 week before the talk (Wednesday, 1pm): submission of an extended abstract
  • The day of the talk (Wednesday, 1pm): submission of a preliminary paper for review
  • 1 week after the talk (Wednesday, 1pm): receiving comments from reviewers
  • 2 week after the talk (Wednesday, 1pm): submission of the final paper