Agenda Machine Learning Week Europe 2024

18 - 19 November 2024, Munich

Today’s LLMs such as ChatGPT show an impressive performance and have the potential to revolutionize our daily life. All these LLMs are based on the Transformer architecture with the Attention mechanism at its core. Due to the quadratic scaling with context length, Attention makes processing of long sequences very expensive. In this talk Maximilian presents xLSTM, a novel architecture for LLMs that scales only linear in context length while still outperforming Transformers on language modeling.

The presentation will describe Böllhoff’s journey to become a data-driven company. The journey is accompanied by the Low Code No Code Data Science Tool KNIME. On this journey Böllhoff will present two use cases which are implemented by using machine learning algorithms and GenAI in order to generate added value at Böllhoff.

The talk will present TotalJob’s learnings and approach taken towards productionizing GenAI / LLMs for building an empathetic, accurate and compliant job search companion (available over WhatsApp). It will cover the product decisions in going from human to LLM chat and techniques used to reduce LLM costs by 70%, with hallucinations, bias and toxicity at near zero %. Finally, the talk will give an outlook on the future path around a multi-modal and the multi-lingual future of conversational journeys.

In this session, Muhammad will give you an in-depth exploration of chatbot innovation applied in a real-world setting at Endress+Hauser. This session will focus on Endress+Hauser’s practical implementation of Large Language Models, combined with the capabilities of Azure’s Semantic & Vector Search and strategically advance Retrieval-Augmented Generation (RAG) approach, to build a chatbot that is not only highly responsive but also remarkably intuitive. Muhammad will provide a comprehensive overview of their approach, detailing the process of integrating technology stacks and navigating the complexities of chatbot design, demonstrating the tangible benefits of these technologies in a real-world, industrial setting.

Even (and more so) with advances in deep neural networks, understanding data remains a central challenge in data science, but central to its value. Data mapping techniques help us to see salient features of our data sets, explore different dimensions of the underlying systems, and support statistical decision making. Christoph will discuss and demonstrate practical methods to data mapping, from dimensional reduction and clustering over self-organizing maps to deep learning-based variational autoencoders.

An effective picker schedule in warehouses in Quick-Commerce addresses the challenge of resource utilization while maintaining low delivery time. The talk focuses on the challenges in running decision science experiments with humans involved, and embracing learnings by strategizing: How to utilize limited and unclean data caused by stochastic activities and human-error in warehouses? How to draw insights while navigating uncertainties? How to optimize operational decision making processes?

The repositioning of empty containers is a critical challenge for global ocean container carriers. Despite port disruptions, Suez canal closures, adverse weather containers need to be readily available for Christmas shipments of consumer products in China, cherry harvest in Chile, or Salmon season in Norway. Central to the optimization is the accurate forecasting of container demands and their surplus. This session will dive into the logistical complexities of empty container repositioning at Hapag.-Lloyd, one of the worlds largest container sipping companies, and highlight the transformative impact of AI forecasting models by software partner iqast in providing precise demand forecasts on a global scale. Join us as we share a decade of insights and innovations from Hapag-Lloyd, illustrating how advanced AI/ML technologies are revolutionizing empty container logistics.

In the age of increasingly complex foundation models, the question arises as to what extent the underlying correlation structures also represent causal effects. In the field of time series analysis, the concept of causality is a central component and there are established techniques for identifying non-causal spurious correlations. The Deep Dive illustrates these concepts and techniques and shows how they can be successfully combined with state-of-the-art ML algorithms. No formulas required!

How do you motivate and guide an existing organization to create and share analytical data products to improve the results of analytics, machine-learning and ai? Thomas will give you insights into Mercedes Benz AG’s data product cookbook that motivates data mesh and data products, supports data consumers, and provides a step-by-step checklist to build a data product – from business model canvas to data models and lifecycle management.

One of the biggest challenges of Artificial Intelligence is its desperately needed transformation from a highly complex fabric of algorithms to a tool as simple as a hammer. Everyone must be able to use it independently of his/her academic background. Therefore, we explore the boosting of sustainable energy usage on the example of Testo data loggers, e.g., by live monitoring and state of charge prediction with survival algorithms. Moreover, we provide AI-assisted services such as the adaptive scheduling of maintenance intervals, the automated detection of ML model drifts as well as easy recalibration and retraining of models when necessary. In this context, our demonstrator also highlights concepts of intuitive interaction and visualization in order to reduce complexity of human interaction with Machine Learning and to empower domain experts to become self-determined AI users.

In many real-world scenarios, like quantitative finance, datasets exhibit a probability distribution with significant skewness. Neglecting fat-tails can lead to increased estimation errors and potential business losses. Niranjana introduces a new classifier, termed Elliptical Discriminant, that generalises Quadratic Discriminant Analysis (QDA) to handle fat-tailed data. This is demonstrated using a multivariate dataset with fat-tails and a comparative study with other well-known classifiers.

Understanding and evaluating the creativity of Language Models and Generative AI is crucial as these technologies integrate into various industries. Key Questions for Table Discussions: 

• What are the most effective metrics for assessing creativity in Language Models and Generative AI? 
• How can we ensure that LLM evaluations are objective and unbiased? 
• What are the potential impacts of AI creativity assessments on future AI development and applications?

We will discuss the following questions, especially in light of the rapid development in AI technology: 1. How should data & analytics functions position themselves within the organization? (e.g., consulting/ supporting role for business units or driving force, pushing the adoption of new technologies) 2. How can data & analytics functions measure and demonstrate their value contribution? 3. What is the required skillset and organizational setup to make the positioning valuable and impactful?

For this table discussion, we want to tackle the following three main questions: 

1. How can organizations successfully implement a Data Mesh architecture, and what challenges might they face during this transition? 
2. What are the key components of a successful Data Product, and how can organizations ensure they deliver real value to stakeholders? 
3. How does the adoption of Data Mesh and Data Products impact organizational culture and team dynamics?

Navigating the complexities of airline claims can be a challenge for both agents and passengers. Claim Summarizer, a novel tool powered by Generative AI (Gen AI), tackles this challenge by providing claim agents with concise, AI-generated summaries of complex claims documents. This presentation explores how Claim Summarizer empowers agents to make faster, informed decisions by highlighting key details and extracting vital information. Moreover, the Claim Summarizer is Lufthansa’s blueprint of future LLM Ops. By implementing the Claim Summarizer, they have established robust LLM Ops processes that can be used in their new products and accelerate the time to market of new Gen AI innovation in the Lufthansa Group.

Special measures must be provided for a highly automated production of safety critical products. Therefore, a system focused on AI-based visual inspections is developed. This should improve the performance, stability and transparency of the particular inspections, the scalability of inspections across assembly lines and especially the quality assurance. The system architecture and the actual implementation for bringing state of the art neural networks into the production will be presented.

Companies implementing AI are caught between prospects of success and societal concerns. Regulations attempt to mitigate the insecurities that arise through the widespread adoption of AI. This session helps corporations struggling to operationalise these standards by providing a step-by-step guide to embed trustworthy AI in their organisations. With a brief foray into strategy, processes & organisational design this talk will show ways to improve the ethical footprint of your company.

OpenAI took an amazing idea – transformers – and sold it like a dream: ask AI. Now every company needs to sell AI-something, no matter what. But what if this craziness could be our best chance to face the truth about connectionism – without the over-excitement about the amazing results – and think again about the next class of problems that are worth solving? It’s time to deeply rethink AI – as long we have money for it – and start looking for really damn good answers, not just good enough ones.

In this talk, John will give you a technical overview of a Gen AI journey and addresses the efficiencies of inference and optimization of compute resources.

Data quality plays a pivotal role in AI, especially when dealing with consumer data. Join Christophe as he delves into entity resolution for consumer data, blending modern machine learning and graph-based algorithms with human expertise, to balance automation, high data quality and manual corrections. He will provide a comprehensive overview of Experian’s data pipeline, addressing the potential and limitations of vector search, and detailing the challenges of ensuring data quality for billions of records on a daily basis.

At KSB SE & Co. KGaA, the number of productive ML-models increased with the growing customer base of its digital product KSB Guard. As a result, the need for a clear separation of responsibilities between data scientists and operations increased. In particular, the further development of already productive models became a pain point. In this talk Simon presents a service architecture that promotes seamless collaboration between data science and operations teams.

Machine learning models should not live in a vacuum. When a predictive model is exposed to the user to enrich a scientific or industrial workflow, incorporating human feedback is essential for the model to improve over time, overcome distribution shifts, and learn novel phenomena. Miha addresses the engineering challenges of building interactive active learning systems on a practical example of large-scale video analysis.

Combining the strengths of panel data and passively measured cookie data is the key to provide the full view on media consumption. This talk highlights how the combination of classical ML and optimization techniques helped to measure digital audiences in Spain in an unbiased, reliable and precise manner. Moreover, the learnings gained during the development of a scalable and modularized pipeline for big data, which components can be easily re-used for other markets or contexts, are discussed.

Model-based process characterisation is key for implementing real time release testing within pharmaceutical manufacturing. Andre illustrates the integration of data-driven modelling and machine learning to craft resilient release strategies capable of accurately predicting the products’ quality attributes. These strategies result in optimised lead times in the supply chain and foster a comprehensive and timely understanding of the process performance, thereby generating substantial value.

RLHF is critical method in NLP which learn from human interactions, generating more accurate and contextually appropriate responses. In this session, Prince will explore what is RLHF: He will start with discussing underlying principles behind it, various techniques used and finally a real-world example including data collection, reward design, and model evaluation to illustrate its effectiveness. By the end Prince will discuss its limitations, how it can be adapted to different use cases and domains.

The attendees will explore how Swiss Mobiliar processes insurance quote recommendations faster and more accurately by unlocking hidden data patterns with NLP-based AI functions embedded in SQL following the paradigm “Bring the algorithms to the data – not the other way around”. An example from the world of soccer will be followed by a discussion of the objectives and results of the app for quote recommendations. Thomas will also discuss accuracy, traceability and trustworthiness of the predictions.

Of all the data projects that fail, 80% fail due to poor communication. When decision makers don’t understand a data product, they don’t need more information: they need less of it. In this talk, Jack and Julia will show how data storytelling is helping to promote data products and get buy-in at a pharma company. Tune in to learn the process of shaping the narrative and finding a data product marketing strategy. Get expert tips on how you can use data storytelling for your own data / AI product.

Keyword based search engines will fail to support random queries like ‘‘red shirt with black collar and avenger cartoon in front” in case the product description has not got these details. In Fashion e-commerce such queries are becoming popular. To support this, we can query product images directly by converting images into multimodal embeddings and then searching on them. This talk will discuss the approach and show how to modify the keyword-based search engine to support such queries.

Migration, inflation, climate change, and more present us with numerous uncertainties when making socio-political or strategic business decisions. How can we still make robust decisions? In kaleidemoskop’s BMBF-funded project, InnoTwin, they are developing a digital twin of German society. This allows them to conduct simulations under various conditions to identify actions that yield robust outcomes across a wide range of scenarios.

For healthcare professionals, treating patients in the best way possible is a challenge in more ways than one. Extensive therapy guidelines – though necessary – contribute to the complexity of their working life. To support treatment decisions, Campana & Schott, together with Charité, developed a smart assistant which recommends treatment according to said guidelines based on the patient’s diagnosis and medical history. Ramón will present you his results and envision potential further applications.

Duplicate records can have a negative impact on many areas of a business. Current methods to detect duplicate records use traditional NLP techniques known as “Entity Matching”. An improvement to this traditional method can be achieved by incorporating GenAI techniques that do not entail any calls to OpenAI. Not only does this produce better matches, but it also keeps the data safe, since no information is transferred externally.

The Table Captains present the three key take-aways from their discussion round.