Conference & Workshops

On April 1^st, 2025, the MLE Day 2025 will be held at the TU Hamburg. 

Its main objective is to foster stronger connections and collaborations within the MLE network and with partners. The program includes selected presentations, a poster session and coffee breaks for networking.

All MLE members and partners are cordially invited to attend. 
If you are interested in becoming a member of MLE, we would also be happy to have you at the MLE Day 2025.

• Date: 01.04.2025
• Time: 9:00 - 17:00
• Location: TU Hamburg, Building H, Room 0.16 (Presentations)
• Address: Am Schwarzenberg Campus 5, 21073 Hamburg

Registration

If you want to attend, please, send an email to Ulrike Schneider (u.schneider@tuhh.de) with your name and affiliation. The registration is open until 01.03.2025. 
The number of participants is limited by the size of the lecture hall. For guaranteeing your participation and to make planning (particularly of the coffee breaks) easier, please register as soon as possible. Your data will only be used for organizing the MLE Days.

Preliminary Program

Catering: There will be a coffee break in the morning and afternoon with hot drinks and snacks. Lunch in the canteen is to be paid for by the participants themselves.

Poster session: If you want to present a poster, please send an email to Ulrike Schneider (u.schneider@tuhh.de) with the abstract and other information attached using the template ( https://cloud.tuhh.de/index.php/s/X4xdesJt2xfZfkN ) in English until 21.02.2025.

If the Word-file or the cloud is not working for you, please send an email with the following information:

Title, 
Authors, 
Presenting author + email address, 
MLE research focus (Please indicate which MLE research focus https://www.tuhh.de/mle/research-focus fits best to your poster.)
Abstract (max. 200 words)

Submitting a poster abstract you are agreeing that the corresponding information can be shared with all participants of the MLE Days 2025.

The organizing committee reserves the right to reject registrations and poster contributions.

If you have any questions, please do not hesitate to contact the organizing team via mle@tuhh.de .

The organizing committee:

• Nihat Ay
• Annika Eichler
• Christian Feiler
• Sebastian Götschel
• Stefan Schulte
• Marcus Venzke
• Gregor Vonbun-Feldbauer
• Jens-Peter Zemke

On September 22^nd - 25^th, 2025, at TU Hamburg.

The conference will have a main session and a session for contributed talks and posters.

Conference Goal

In recent years, the field of Machine Learning has made significant progress in theory and applications. This success is rooted in the mutual stimulation of mathematical insight and experimental studies. On the one hand, mathematics allows to conceptualize and formalize core problems within learning theory, leading, for instance, to performance bounds for learning algorithms. On the other hand, experimental studies confirm theoretical predictions and instigate new directions in theoretical research. This meeting aims to discuss the interaction between theory and practice, with focus on the current gaps between the two. The talks will be centered around themes including the following.

• Gradient Methods (gradient optimization, stochastic gradient, natural gradients, gradient applied to deep networks, ...),
• Natural Geometric Structures (Information Geometry, optimal transport geometry, ...),
• Generalisation Theory (statistical learning theory, complexity measures, Ill-posed inverse problems, regularization, implicit bias...)
• Functional analytical tools (approximation theory, harmonic analysis, ...)
• Overparametrization and random matrix theory (neural tangent kernel, lazy training, convergence of gradient descent, generalization bounds, ...)

Organisers

• Nihat Ay   Hamburg University of Technology, Germany and Santa Fe Institute, USA
• Martin Burger   DESY and University of Hamburg, Germany
• Benjamin Gess   TU Berlin and Max Planck Institute for Mathematics in the Sciences, Germany
• Guido Montúfar   University of California, Los Angeles, USA and Max Planck Institute for Mathematics in the Sciences, Germany

Scientific Committee

• Alexandra Carpentier  University of Potsdam, Germany
• Asja Fischer  Ruhr University Bochum, Germany
• Armin Iske  University of Hamburg, Germany
• Stefanie Jegelka  Massachusetts Institute of Technology, USA and Technical University of Munich, Germany
• Parvaneh Joharinad  Leipzig University and Max Planck Institute for Mathematics in the Sciences, Germany
• Sören Laue  University of Hamburg, Germany
• Johannes Lederer  University of Hamburg, Germany
• Marco Mondelli  Institute of Science and Technology, Austria
• Sayan Mukherjee  Leipzig University, Germany
• Liza (Elizaveta) Rebrova  Princeton University, USA
• Gabriele Steidl  TU Berlin, Germany
• Diaaeldin Taha  Max Planck Institute for Mathematics in the Sciences, Germany
• Melanie Weber  Harvard University, USA
• Jens-Peter M. Zemke  Hamburg University of Technology, Germany

For more details, please visit the conference page.

"Guided Self-Organization: Machine Learning in Embodied Agents"

Call for submission by August 31st, 2024
 

The 11th International Conference on Guided Self-Organization takes place during 12-14 February 2025 in Tübingen, Germany.

GSO-2025 is organized by

• The University of Tübingen,
• The Hamburg University of Technology, 
• The Max Planck Institute for Intelligent Systems, and 
• The International Association for Guided Self-Organization (TIA-GSO).

The main theme of GSO-2025 is "Guided Self-Organization: Machine Learning in Embodied Agents"

The GSO-2025 conference will bring together invited experts and researchers in machine learning, artificial life, self-organizing systems, and complex adaptive systems, with particular emphasis on autonomous agents, information theory, critical phenomena and emergent behaviour.  Special topics of interest include: reinforcement learning, intrinsic motivations, origin of life, systems biology, physics of life, unconventional computation, swarm intelligence, measures of complexity, criticality, complex networks, information-driven self-organization (IDSO), etc.

The program will include three days, with five keynote talks, and a number of regular onsite presentations on each day. There are no registration fees for the conference.

If interested in participating, please submit an extended abstract (up to two pages, pdf) by August 31^st, 2024, via a Google form:

https://docs.google.com/forms/d/e/1FAIpQLSfVLeAS66Vngnkb6Zar3F2hI6EZAAJQFTmDurPx7qp_7BYB2A/viewform

The notifications are expected by September 30^th, 2024.

On September, 25th to 27th, 2023, the third MLE Days on machine learning in engineering on the campus of the Hamburg University of Technology (TUHH).

This year, it combines a summer school with a one-day startup-challenge. Participation is free of charge, but a registration is required.

The Summer School teaches insights into the world of machine learning with a focus on engineering. It provides sessions about fundamentals of machine learning, concrete application examples, as well as hands-on sessions to try out and consolidate lessons learned. Keynote talks complete the program. Three parallel tracks are provided to allow participants to choose contributions adapted to their interest and machine learning experience. The use cases range from sensor and image processing, to electrical engineering and materials science, to aviation and maritime logistics. A poster session and an elevator pitch event allow participants to present their own work on machine learning topics. The best posters and pitches will be selected by a jury and awarded prizes. A networking event allows attendees to establish contacts with selected corporate partners and sponsors from start-ups and medium-sized businesses to large corporations. In the startup-challenge attendees learn how to turn machine learning ideas into a business.

The MLE Days are organized by the Machine Learning in Engineering research initiative of the TUHH (MLE@TUHH) in collaboration with the Helmholtz Center Hereon, DASHH, and the Career Center of TUHH, the AI.Startup.Hub, and AI.HAMBURG. The MLE initiative joins the competencies in the field of machine learning at the Hamburg University of Technology with the goal of transferring knowledge towards business and industry. Students, PhD students, postdocs, and professors from all disciplines of the TUHH are engaged together with colleagues from the Helmholtz Center Hereon to make methods and applications of machine learning known, to network, and to foster scientific exchange.

On September 15 & 16, 2022, we are organizing the two-day conference “MLE-Days 2022”. It will give participants a broad and well-founded insight into engineering and operational fields of application of machine learning.

This year's range of topics covers many areas of engineering: Aeronautical Engineering, Civil Engineering, Maritime Logistics, Process Engineering, Materials Science, Energy Engineering, etc. In addition, machine learning methods for special topics such as language processing, cyber-physical systems and particle accelerators will be covered in depth. The speakers come from both academic and industrial backgrounds. In three keynotes, we will look beyond the horizon and discuss, for example, ethical aspects of machine learning methods or the limits of such methods.

New this year is a session in which start-up companies with ML applications can present themselves. There will also be sessions in which companies can present their MLE use cases from practice. We are calling on companies to participate in these sessions with contributions, a corresponding call has already been published.

The MLE Days 2022 will be complemented by the MLE Summer School 2022. This event will take place on the two days before the MLE Days and is aimed at doctoral and master's students. MLE Days 2022 participants automatically have access to the Career Event, which concludes the second day of the MLE Summer School 2022.

On September 13 and 14, the first MLE Summer School for Machine Learning in Engineering will take place at Hamburg University of Technology.

Machine learning has become a driving force of economic innovation and development. It also plays a key role in many academic research projects. With the ubiquitous application of machine learning techniques to solve current problems, it can be overwhelming to keep up with current developments. Therefore, TUHH is organizing a two-day summer school that offers insights into fundamentals and theories as well as hands-on training in the application of machine learning in engineering. The “MLE School 2022” makes it possible to exchange ideas with like-minded people during the social event or the poster and networking sessions and to broaden your own horizons.

The event is open to Master's students and doctoral candidates as well as postdocs from universities and related institutions.

On July, 1st and 2nd, 2021

MLE together with MathWorks organizes two online events that take place one week apart:

• Machine Learning with MATLAB (05.11.2020, 14:00-17:00)
• Deep Learning with MATLAB (12.11.2020, 14:00-17:00)

The events are free for members of TUHH and HZG.

Both events will include

• Industry/research examples using MATLAB for ML/DL
• Complete ML/DL workflow using real-world ECG Data (signal processing, referencing image processing in the DL)
  • emphasis on feature engineering, model selection and tuning
  • comparison with automated machine learning (eliminating manual steps required to go from a data set to a predictive model)
  • tips and tricks

Engineers and scientists use AI techniques on large amounts of data in various formats, and across different domains and industries.

In two interactive sessions, we show examples of engineers and scientists using MATLAB for building AI-driven systems. We explore the complete workflow of developing machine learning and deep learning applications with MATLAB using a real-world ECG data set. We also show how to easily develop and apply data analytics solutions that take advantage of enhanced signal processing and AI techniques, including automated feature extraction, model selection and tuning.

We recommend taking the free, two-hour interactive introductions to practical machine learning methods and deep learning methods, respectively, before each session. In between the two sessions, participants will have access to the used data set, to apply your acquired knowledge and share their achieved results. The second session does not have the first session as a prerequisite and can be attended independently.

You receive access to

• complete workshop materials
• data sets, software & GPU resources during the workshops
• data sets in between the workshops, so that participants can try to tune the models and share their results two days before the second workshop

The event will take place via Zoom. Registration for the events is open until 20.10.2020. If you intend to participate:

• TUHH: please register in the Stud.IP group MLE@TUHH: MLE with MATLAB
• HZG: please write an email to Jens-Peter M. Zemke indicating that you wish to participate.

Download Flyer

• Portrait
• Landscape

Objective

Machine-Learning in Engineering (MLE@TUHH) is an initiative to bundle competencies in the field of machine learning at the TUHH with the aim of transferring knowledge to business and industry. On November 4, 2020 at 10:00 a.m. MLE would like to introduce itself to all members of the Hamburg University of Technology. The event is aimed at all members of the TUHH, from institute directors to students. We want to draw attention to the various offers of the MLE initiative and promote the exchange of information within the university. Overall, the aim is to increase the visibility of machine learning activities within the TUHH, promote cooperation and give interested students an insight. The anchoring of MLE in teaching should also be highlighted.

Agenda

• Greeting by the Executive President of the TUHH Prof. Dr. Andreas Timm-Giel
• Welcome & introduction by MLE@TUHH spokespersons Prof. Dr. Christian Schuster & Prof. Dr. Volker Turau
• Presentation of the study program “Data Science” by Prof. Dr. Tobias Knopp
• 3 pitches by PhD students (from various fields) on how they apply ML in their research
  • Nicolas Rückert - Machine Learning in combination with Operations Research (slides)
  • Daniel Schoepflin - Synthetic training data for industrial object recognition (slides)
  • Florian Meyer - Reinforcement learning for the Industrial Internet of Things (slides)
• Presentation of cooperation partner Artificial Intelligence Center Hamburg e.V. (ARIC) by CEO Alois Krtil
• Conclusion: Concretely planned projects. Why should you join the ML initiative? What makes us special? By MLE@TUHH Vice Speaker Prof. Dr. Christoph Ihl & Prof. Dr. Thomas Wrona

Time

• 4.11.2020 at 10:00 am to 11:30 am

Place

• via zoom (invitation via email@tuall)