DataNinja sAIOnARA 2024 Conference

We are excited to invite you to the Data-NInJA DataNinja sAIOnARA 2024 Conference, which will take place from June 25th to June 27th, 2024 at Bielefeld University.

Conference Information

25^th to 27^th of June 2024
CITEC Building, Bielefeld University
Organizers: Barbara Hammer, Ulrike Kuhl

~~Register Now!~~

~~Call for Posters~~

Important Dates

Online Proceedings

Embracing the theme of “shaping Trustworthy AI”, we will bring together researchers, industry experts, and enthusiasts to explore the latest developments and future prospects in artificial intelligence.

Program

Program at a Glance (download .pdf)

Tuesday, 25.06.2024 New Developments in Trustworthy AI
13:30-14:20	Registration & Welcome Coffee
14:20-14:30	Welcome Address
14:30-15:15	Keynote I: Scalable Architectures for Neuromorphic Machine Learning Prof. Dr. Anand Subramoney University of London
15:15-16:00	Keynote II: Scientific Machine Learning for Partially Observed Dynamical Systems Prof. Dr. Kerstin Bunte University of Groningen
16:00-16:30	Coffee Break
16:30- 17:15	Keynote III: How and Why AI Will Shape the Future of Science and Engineering Prof. Dr. Holger Hoos RWTH Aachen University
17:15- 18:00	Keynote IV: Deep Learning for Large-Scale Tree Carbon Stock Estimation From Satellite Imagery Prof. Dr. Christian Igel University of Copenhagen

Wednesday, 26.06.24 AI in NRW – Opportunities and Needs
09:30-10:00	Registration & Welcome Coffee
10:00-10:15	Welcome Addresses Rectorate of Bielefeld University Prof. Dr. Andrea Kienle Head of the Department of Research MKW NRW
10:15-10:45	Overview of AI research in NRW and the NRW Graduate Network DataNinja Prof. Dr. Barbara Hammer Bielefeld University
10:45-11:00	Short Break
11:00- 12:30	DataNinja Spotlights Results and Insights from the PhD projects
12:30- 14:00	Lunch Break with Poster Session
14:00- 15:30	Highlights KI-Starter Program I Prof. Dr. Andrea Horbach: Educational Natural Language Processing – How Language Technology Supports Teachers and Learners Dr. Robin Chan: Generative Modeling of Object Keypoints for 6D Pose Estimation Dr. Petra Bevandić: Leveraging Class Relations for Multi-Dataset Semantic Segmentation Prof. Dr. Zorah Lähner: Machine Learning in Between Discrete and Continuous Settings Dr. France Rose: Missing Data? Keep Calm and Use DISK (Deep Imputation of SKeleton data) Dr. Friedrich Solowjow: Event-triggered Learning and Similarity of Dynamical Systems
15:30- 16:30	Panel Discussion: “AI – Needs and Risks”
16:30- 17:00	Coffee Break with Poster Session
17:00- 17:45	Keynote V: Perspective Taking in Large Language Models Prof. Dr. Lucie Flek University of Bonn
17:45- 18:30	Keynote VI: LLM-based Argument Quality Improvement Prof. Dr. Henning Wachsmuth Leibniz University Hannover
from 18:30	Conference Dinner

Thursday, 27.06.2024 Evaluation and networking “AI made in NRW”
09:30-10:00	Registration & Welcome Coffee
10:00-10:45	Keynote VII: Trustworthy AI for Physical Machines: Integrating Machine Learning and Control Prof. Dr. Sebastian Trimpe RWTH Aachen University
10:45-11:00	Short Break
11:00-12:30	Highlights KI-Starter Program II Dr. Leonardo Galli: Don’t be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models Dr. Daniel Horn: Optimal Data Rotations for Trees and Forests Prof. Dr. Tanya Braun: What Can Explainability Mean for Probabilistic Inference? Dr. Kira Maag: Out-of-Distribution Segmentation via Pixel-wise Gradient Uncertainty Prof. Dr. Benjamin Risse: A Glimpse into Quantifying Machine Intelligence and its Limitations Dr. Andrew Melnik: Semantic Reasoning and Goal Understanding for Home-Robotics
12:30-13:30	Networking Lunch
13:30-15:00	Networking break: SAIL Poster Session
15:00-15:45	Keynote VIII: Biological Biases for Learning Robust Robot Behavior: Does Deep Reinforcement Learning Run into the Alignment Problem? Prof. Dr. Malte Schilling University of Münster
15:45-16:15	Coffee Break
16:15-16:45	Award Ceremony for Outstanding Poster Presentation
16:45-17:00	Closing Remarks & Farewell

Tuesday, 25.06.2024

DAY 1: New Developments in Trustworthy AI
13:30-14:20	Registration and Welcome Coffee
14:20-14:30	Welcome Address
14:30-15:15	Prof. Dr. Anand Subramoney Department of Computer Science, Royal Holloway, University of London	Keynote I: Scalable Architectures for Neuromorphic Machine Learning I will discuss how to design architectures for neuromorphic machine learning from first principles. These architectures take inspiration from biology without being constrained by biological details. Two major themes will be sparsity and asynchrony, and their significant role in scalable neuromorphic systems. I will present recent work from my group on using various forms of sparsity and distributed learning to improve the scalability and efficiency of neuromorphic deep learning models.
15:15-16:00	Prof. Dr. Kerstin Bunte Professor of Machine Learning for Interdisciplinary Data Analysis Head of Intelligent Systems Group, University of Groningen	Keynote II: Scientific Machine Learning for Partially Observed Dynamical Systems Nowadays, most successful machine learning (ML) techniques for the analysis of complex interdisciplinary data use significant amounts of measurements as input to a statistical system. The domain expert knowledge is often only used in data preprocessing. The subsequently trained technique appears as a “black box”, which is difficult to interpret and rarely allows insight into the underlying natural process. Especially in critical domains such as medicine and engineering, the analysis of dynamic data in the form of sequences and time series is often difficult. Due to natural or cost limitations and ethical considerations data is often irregularly and sparsely sampled and the underlying dynamic system is complex. Therefore, domain experts currently enter a time-consuming and laborious cycle of mechanistic model construction and simulation, often without direct use of the experimental data or the task at hand. We now combine the predictive power of ML and the explanatory power of mechanistic models. Therefore we perform learning in the space of dynamic models that represent the complex underlying natural processes, with potentially very few and limited measurements. We use principles of dimensionality reduction, such as subspace learning, to determine relevant areas in the parameter space of the underlying model as a first step to achieve task-driven model reduction. We furthermore incorporate identifiability analysis for informed posterior construction to improve learning with ill-posed systems caused by data limitations. Findings indicate the possibility of an alternative handling of epistemic uncertainties for scientific machine learning techniques applicable for all linear and classes of non-linear mechanistic models based on Lie symmetries. Joint work of: Bunte, Kerstin; Tino, Peter; Oostwal, Elisa; Norden, Janis; Chappell, Michael; Smith, Dave
16:00-16:30	Coffee Break
16:30- 17:15	Prof. Dr. Holger Hoos Alexander von Humboldt Professor of Computer Science Faculty of Mathematics, Computer Science and Natural Sciences, RWTH Aachen	Keynote III: How and Why AI Will Shape the Future of Science and Engineering Recent progress in artificial intelligence has elevated what used to be a highly specialised research area to a topic of public discourse and debate. In this presentation I will discuss why beyond the hype, there are good reasons to be excited, but also concerned about AI. Specifically, I will explain how and why AI will have transformative impact on all sciences and engineering disciplines. Based on my own research on the robustness of neural networks, I will discuss some of the fundamental strengths, weaknesses and limitations of current AI systems. Finally, I will share some thoughts on the most serious risks of deploying these systems quickly and broadly, as well as on what needs to be done in order to manage these risks and to realise the benefits AI can bring.
17:15- 18:00	Prof. Dr. Christian Igel Department of Computer Science, University of Copenhagen Director of the SCIENCE AI Centre, University of Copenhagen	Keynote IV: Deep Learning for Large-Scale Tree Carbon Stock Estimation From Satellite Imagery Trees play an important role for carbon sequestration, biodiversity, as well as timber and food production. We need a better characterization of woody resources at global scale to understand how they are affected by climate change and human management. Recent advances in satellite remote sensing and machine learning (ML) based computer vision makes this possible. This talk discusses large-scale mapping of individual trees using deep learning applied to high-resolution satellite imagery. The biomass of each tree, and thereby its carbon content, is estimated from the crown size using allometric equations. The parameters of these equations are learned from data. The functional relation is assumed to be non-decreasing. Such monotonicity constraints are powerful regularizers in ML in general. They can support fairness in computer-aided decision making and increase plausibility in data-driven scientific models. This talk introduces a conceptually simple and efficient neural network architecture for monotonic modelling that compares favorable to state-of-the-art alternatives. After this technical excursion, we present an application of our tree monitoring in Rwanda, where it helps quantifying progress of restoration projects and developing a pathway to reach the country’s goal of net zero emissions by 2050.

Wednesday, 26.06.24

DAY 2: AI in NRW – Opportunities and Needs
09:30-10:00	Registration & Welcome Coffee
10:00-10:15	Welcome Address by Rectorate of Bielefeld University Opening Remarks by Prof. Dr. Andrea Kienle, Head of the Department of Research, Ministry of Culture and Science NRW
10:15-10:45	Prof. Dr. Barbara Hammer Professor of Machine Learning Head of Machine Learning Group, Bielefeld University	Overview of AI research in North Rhine-Westphalia and the NRW Graduate Network DataNinja
10:45-11:00	Short Break
11:00- 12:30		DataNinja Spotlights Results and Insights from the PhD projects
12:30- 14:00	Lunch Break with Poster Session
14:00- 15:30	Highlights KI-Starter Program I Prof. Dr. Andrea Horbach University of Hildesheim Educational Natural Language Processing – How Language Technology Supports Teachers and Learners Dr. Petra Bevandić Bielefeld University Leveraging Class Relations for Multi-Dataset Semantic Segmentation Dr. France Rose University of Cologne Missing data? Keep Calm and Use DISK (Deep Imputation of SKeleton data)		Dr. Robin Chan Bielefeld University / TU Berlin Generative Modeling of Object Keypoints for 6D Pose Estimation Prof. Dr. Zorah Lähner University of Bonn Machine Learning in Between Discrete and Continuous Settings Dr. Friedrich Solowjow RWTH Aachen University Event-triggered Learning and Similarity of Dynamical Systems
15:30- 16:30	Panel Discussion: “AI – Needs and Risks” Prof. Dr. Klaus Neumann Bielefeld University Anja Moldehn Centrum Industrial IT, Lemgo	Dr. Sebastian Walter weav.ai, Mountain View, CA, USA Prof. Dr.-Ing. Roman Dumitrescu Fraunhofer IEM, Paderborn Dr. Felix Reinhart Miele	Prof. Dr. Daniel Neider TU Dortmund University Research Center Trustworthy Data Science and Security Dr. Julia Fröhlich HARTING Technology Group
16:30- 17:00	Coffee Break with Poster Session
17:00- 17:45	Prof. Dr. Lucie Flek Professor of Data Science & Language Technologies, University of Bonn	Keynote V: Perspective Taking in Large Language Models Perspective-taking, the process of conceptualizing the point of view of another person, remains a challenge for LLMs. Understanding the mental state of others – emotions, beliefs, intentions – is central for the ability to empathize in social interactions. It is also the key to choose the best action to take next. Enhancing perspective-taking capabilities of LLMs can unlock their potential to react better and safer to hints of distress, to engage in a more receptive argumentation, or to target an explanation to an audience. In this talk, I will present our recent perspective-taking experiments, and discuss further opportunities for bringing the human-centered perspectivist paradigm into the LLMs.
17:45- 18:30	Prof. Dr. Henning Wachsmuth Head of the Natural Language Processing Group Leibniz University Hannover	Keynote VI: LLM-based Argument Quality Improvement Natural language processing (NLP) has recently seen a revolutionary breakthrough, due to the impressive capabilities of large language models (LLM). This also affects NLP research on computational argumentation: the computational analysis and synthesis of natural language arguments. While one of the core tasks studied in computational argumentation is the assessment of an argument’s quality, in this talk I look one beyond, namely at how to improve argument quality. Starting from basics of argumentation, I present insights from selected research of my group involving LLMs for improving argument quality. As part of this, I also look at the recent breakthroughs of LLMs and the paradigm shift that comes with them for computational argumentation in particular and for NLP in general.
from 18:30	Conference Dinner

Thursday, 27.06.24

DAY 3: Evaluation and networking “AI made in NRW”
09:30-10:00	Registration & Welcome Coffee
10:00-10:45	Prof. Dr. Sebastian Trimpe Professor and Head of Institute for Data Science in Mechanical Engineering, RWTH Aachen University	Keynote VII: Trustworthy AI for Physical Machines: Integrating Machine Learning and Control AI promises significant advancements in engineering, enhancing both design and operation processes. Given that engineering focuses on physical machines like vehicles or robots, ensuring trustworthy solutions is crucial. This talk will explore how combining classical control methods with modern machine learning can create reliable algorithms for real-world applications. Specifically, we will discuss some of our recent research on (i) Bayesian optimization for controller learning, (ii) deep reinforcement learning, and (iii) approximate model-predictive control via imitation learning. The effectiveness of the developed algorithms will be demonstrated through experimental results on robotic hardware.
10:45-11:00	Short Break
11:00-12:30	Highlights KI-Starter Program II Dr. Leonardo Galli LMU Munich Don’t be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models Prof. Dr. Tanya Braun University Münster What Can Explainability Mean for Probabilistic Inference? Prof. Dr. Benjamin Risse University Münster A Glimpse into Quantifying Machine Intelligence and its Limitations		Dr. Daniel Horn TU Dortmund Optimal Data Rotations for Trees and Forests Dr. Kira Maag TU Berlin Out-of-Distribution Segmentation via Pixel-wise Gradient Uncertainty Dr. Andrew Melnik Bielefeld University Semantic Reasoning and Goal Understanding for Home-Robotics
12:30-13:30	Networking Lunch
13:30-15:00	Networking Break: SAIL Poster Session
15:00-15:45	Prof. Dr. Malte Schilling Head of the Autonomous Intelligent Systems Group University of Münster	Keynote VIII: Biological Biases for Learning Robust Robot Behavior: Does Deep Reinforcement Learning Run into the Alignment Problem?
15:45-16.15	Coffee Break
16:15-16:45	Award Ceremony for Outstanding Poster Presentation
16:45-17:00	Closing Remarks & Farewell

Registration

~~Participation is free of charge, however, advance registration is required and will close on May 31st, 2024! Register now!~~

Registration is now closed. We look forward to welcoming all registered participants in Bielefeld!

Call for Posters!

The deadline for poster submissions has now passed. Thank you to everyone who submitted their work. The review process is currently underway, and poster authors will be informed of the results by May 24th, 23.59h CEST. We look forward to showcasing the selected posters at the conference!

We are excited to invite researchers, particularly junior researchers, to participate in the poster session at the DataNinja sAIOnARA 2024 Conference. You will have the chance to present your poster on Wednesday, June 26th, from 12.30-14.00h and again from 16:30-17:00h.

We welcome submissions of current work at any stage of the research process. Submission may also offer conceptual syntheses of existing knowledge to present a cohesive new concept or idea. If you’re exclusively submitting previously published work, make sure to clearly state where your work has appeared before at the beginning of the abstract. While previously published work is acceptable for presentation at the conference, note that the selection committee may decide not to include it in the conference proceedings to prevent double publication and maintain the integrity of academic publishing standards.

Contributions can cover a wide range of topics within the realm of trustworthy AI, including but not limited to:

Ethical considerations in AI development and deployment
Transparency and explainability in AI algorithms
Fairness and bias mitigation strategies
Privacy-preserving AI technologies
Robustness and resilience of AI systems against adversarial attacks
Accountability and responsibility in AI decision-making
Human-centered AI design and interaction

Why Participate?

Showcase your research to a diverse audience of AI enthusiasts and experts!
Gain valuable feedback and insights from fellow researchers and professionals!
Secure a chance at winning the DataNinja 2024 Poster Prize!
Network with peers and potential collaborators!
Elevate your profile in the AI community!
All accepted contributions will be published in our proceedings collection!

Submission Guidelines

Submissions should consist of a short, extended abstract of up to two pages excluding references.
Use the following Latex template for your submission: Latex Template DataNinja sAIOnARA 2024 Conference
Please send your abstract via email to contact@dataninja.nrw by May 10th, 2024, 23:59h CEST, with the subject line “sAIOnARA 2024: Poster Abstract Submission.”

Selection Process:

Submitted contributions will undergo a thorough review process by the organizers.
All selected contributions will be published as conference proceedings.

Poster guidelines:

Please pay attention to the following when preparing your poster:

Prepare your poster in A0-size format: 118.9 cm (height) x 84.1 cm (width), portrait orientation
State the title and the authors at the top of your poster in easily readable letters
Indicate the presenting author if different from the first author
Disclose any potential conflicts of interest
Of you’re presenting previously published work, make sure to clearly state where your work has appeared before.
The text and the illustrations should be readable from a distance of 1.5 meters – consider the following suggested specifications:
- Title: 90 pt, Authors: 50 pt, Headings: 36 – 44 pt, Text: 28 – 34 pt
- Use sans serif font (e.g., Arial or Helvetica, not Times New Roman)
- Avoid writing in ALL CAPS or fancy fonts

Presentation:

The poster presentation will be in-person only, meaning that at least one of the authors is required to register and attend the conference.
Dedicated poster presentation time is on Wednesday, June 26th, from 12.30-14.00h and again from 16:30-17:00h. During these times, the presence of at least one of the authors at the poster is required.
There is the option to display the poster throughout the entire duration of the conference.

Don’t miss this opportunity to share your work. We look forward to receiving your submissions and seeing you at the DataNinja sAIOnARA 2024 Conference!

Important Dates

25.03.24

Registration open!

Call for posters announced

10.05.24

23:59h CEST

Poster abstract submission deadline

until 24.05.24

Poster abstract acceptance notification

31.05.24

23.59h CEST

Registration closes

25.06.24

13.30h CEST

Start of conference

26.06.24

12.30-14.00h / 16.30-17.00h CEST

Poster presentation sessions

27.06.24

15.45-16.15h CEST

Award ceremony for
outstanding poster and
exhibit piece

27.06.24

16.30h CEST

Closing of conference

Late summer 2024

Publication of conference proceedings

Contact

If you have any questions or require further information, please do not hesitate to reach out at contact@dataninja.nrw.

DataNinja sAIOnARA 2024 Conference

Program

Registration

Call for Posters!

Why Participate?

Submission Guidelines

Selection Process:

Poster guidelines:

Presentation:

Important Dates

Contact

One Reply to “DataNinja sAIOnARA 2024 Conference”