CAIML #34
Meetup Cologne
The 34th meetup of the Cologne AI ML (CAIML) community took place on January 21 at congstar in Cologne. After the turn of the year, we were pleased to see more than 80 CAIML enthusiasts in person again and to spend an evening with them enjoying interesting lectures and stimulating discussions.
Venue
The CAIML #34 meetup took place at congstar GmbH in Cologne. Enclosed impressions from the numerous meetups in 2024 with a high rate of participation from AI and ML enthusiasts.
Agenda
Talk 1
Jonas Deichmann (Data Scientist at congstar): “Within the Horizon: Forecasts for Service Hotlines”
Discussion on how machine learning can improve call center operations, we’ll cover:
- Forecasting Techniques: Using models like XGBoost to predict contact volumes.
- Operational Efficiency: Enhancing agent planning with accurate forecasts.
- Cost Management: Reducing costs through precise forecasting.
Talk 2
Bonald Ziyue LI (Assistant Professor at University of Cologne) – “One Fits All? Towards a Generalist Agent for Smart Mobility based on Meta Reinforcement Learning”
“Smart mobility and transportation are essential components of modern smart cities. Real-time decision-making in smart transportation systems presents significant spatial-temporal complexity. Reinforcement learning (RL)-based agents have emerged as promising solutions for automating such decisions, applied in areas such as autonomous driving, route planning, and traffic signal control – integrating vehicles, humans, and infrastructure into cohesive systems. However, most current RL models are environment-specific, meaning a model trained in one city (e.g., Cologne) is typically effective only within the same environment. This lack of scalability and generalization poses a critical challenge. This talk explores the potential to develop a generalist agent capable of overcoming this limitation – one that is trained in Cologne but deployable in Berlin. Using traffic signal control as a case study, we will discuss innovative approaches to training, model design, and knowledge sharing that enable the development of such adaptable, general-purpose agents.”
Launching Session
Dr. Fabian Hadiji launching the CAIML meetup at the congstar location.
Fabian @fabianhadiji just launched #CAIML no. 34 #meetup of the Cologne #AI #ML Community at #congstar in #Cologne. @CologneAIML pic.twitter.com/hEDTdgjoZy
— Thomas Fabula (@TFConsult) January 21, 2025
Impressions
Dr. Fabian Hadiji
As always, Fabian gave an exciting and entertaining introduction to the evening program and the upcoming lectures.
Christopher Monschau
Chris, our host & sponsor, gives us an overview of the history and corporate purpose of congstar, as well as the current business developments.
Jonas Deichmann
In his very inspiring talk, Jonas explained how XGBoost can be used to make forecasts for service hotlines at congstar. He also discussed the role of explainable AI in ensuring transparency.
Bonald Ziyue LI, Ph.D.
Bonald, an assistant professor at the University of Cologne, gave an absolutely engaging presentation on future intelligent mobile possibilities, i.e. smart mobility. In particular, he discussed how meta reinforcement learning (RL) can enable scalable, adaptable AI solutions for smart cities. Taking the city of Cologne as an example, he showed how generalist RL agents can learn and be deployed in other cities. Bonald provided numerous other illustrative examples of RL and its possible applications in practice.
Slides
- Bonald : drive.google.com/file/smart_mobility
Q & A
What excites you most about AI´s role in smart cities?
Further information
CAIML aims to bring together people interested in AI and ML (machine learning). For more information visit & join us:
Please follow our CAIML community also on Linkedin:
Retrospective
Don’t miss the previous meetups of the CAIML community in Cologne:
Next meetup
Join us on march 18th: www.meetup.com/CAIML/35/