CAIML #29

CAIML #29 is going to happen on March 19, 2024, at BRICKMAKERS GmbH. We will have three talks this time and also time for networking.

Talk 1: Youness Dehbi - Professor of Computational Methods at HafenCity Universität Hamburg: AI & Machine Learning for Digital Twins & Smart Cities

In the era of smart cities, 3D semantic city models are a hot topic. The automatic acquisition of such models is usually facing two challenges: coping with huge and noisy data and dealing with sparse observations. The first obstacle needs strong models to reflect the variety and cope with the complexity of cities. To overcome the second barrier, probabilistic reasoning supported by strong prior knowledge is a key issue to generate reliable and accurate models. On the one hand, we present advanced and cutting-edge machine learning methods allowing for both relational structure description and sound statistical inference. This enables an automatic derivation of a wide range of rules for the reconstruction and interpretation of outside building models. On the other hand, these interpreted models represent a bridge to derive corresponding indoor models based on probabilistic reasoning from sparse noisy data subsequently. The semantically rich acquired models pave the way for smart city applications as digital twins of their real-world counterparts.

Talk 2: Emil Bohleber - Software Engineer at BRICKMAKERS: Rag Optimazatio

In recent times, as Large Language Models (LLMs) have gained popularity in the tech world, there’s been a big push to find ways to make these models even better by feeding them data that’s specific to certain areas or topics. One of the standout methods for doing this is called Retrieval Augmented Generation, or RAG for short. But, like anything else, RAG comes with its own set of issues, such as Vector similarity and vector space density issues, or sparse retrieval challenges. In my talk, I’ll dive into some strategies that have shown promise in tackling these issues. We’ll go through examples to see these strategies in action and we’ll take a look at some code to understand how these solutions work in practice, and what kind of improvements we might expect from them.

Talk 3: Peter Jung - Bayes GmbH: Quo Vadis LLM Agentsn

To understand how LLM agents will impact our world, we need to look beyond the horizon. Let us explore what this hyped, new technology might bring us. This non-technical talk by Dr. Peter Jung from Bayes GmbH is intended for a tekkie audience.

Big thanks to BRICKMAKERS for supporting this event! 🙏 Stay tuned for more details and sign up now