Skip to main content

Workshops

The workshops will take place on May 30 – 31, 2024, in the Circle, Zurich (Flughafen CH, 8058 Zürich)

In order to attend a workshop, make sure you buy a 2-day pass and select the corresponding workshop. Workshops are limited in capacity and served on a first come basis.

Morning Session (09:00 – 12:30)

AI Developer Workshop

Discover how generative AI enables businesses to develop better products and services and deliver original content tailored to the unique needs of customers and audiences. At the second part, the attendees will interact with and prompt engineer LLaMA-2 models to analyze documents, generate text, and be an AI assistant.

Afternoon Session (13:30 – 17:00)

Generative AI for Well-being

Generative AI has reached broad attention in the media over the last months. Different new use cases have been identified to support people in their daily work and make their work more efficient. But what about the well-being of the individuals? Different studies have shown that there is a rise of stress, also in Switzerland. The new technologies bring potential for applications to help people to fight stress and increase their well-being. For example, chatbots or coaching technologies can support mental health or therapy in the setting of blended therapy. On the other side, there is a huge potential of multimedia interventions for elderly people, patients or stressed workers. In this interdisciplinary workshop, we explore what different directions are possible and how these latest technologies can be applied for the well-being of humans. The workshop consists of a series of talks, and a hands-on part.

Morning Session (09:00 – 12:30)

Web Crawling at Scale

Unlock the potential of web crawling with our comprehensive 3-hour workshop! This hands-on tutorial will lead you through the fundamental aspects of web scraping, covering everything from understanding its use cases to overcoming challenges and deploying your own web crawlers. Our experts will showcase a range of successfully implemented web crawling projects across various industries. Additionally, our experienced mentors will provide hands-on assistance with coding exercises in Jupyter Notebooks Environments hosted on the cloud. Whether you’re a beginner or have some experience, this workshop caters to various levels of expertise.

Afternoon Session (13:30 – 17:00)

DataScience in Spatial Computing – explore your data using PlotAR

Did you ever dream about fully immersing yourself in your data, walking through it, grasping it with your hands? Learn with some hands-on exercises the basics of PlotAR. If you bring your own data there will be time to start exploring it during the workshop.

Morning Session (09:00 – 12:30)

AI in Action: A Practical Guide to using Agents for Integrating Custom Knowledge with Large Language Models

This workshop explores Retrieval Augmented Generation (RAG) in Large Language Models (LLMs), focusing on the integration of custom knowledge bases and the use of agents in the generation process. Attendees will learn about the two main components of RAG: retrieval and generation. The retrieval process involves extracting relevant information from structured and unstructured data using methods like text embeddings and additional algorithms of information retrieval. In the generation phase, the model generates contextually appropriate responses by conditioning the LLM on both the input query and retrieved information. The workshop also delves into the role of agents, which are managed by an orchestrator that delegates tasks and condenses results into valuable answers for the user. By combining RAG with agents, the workshop aims to enhance the performance of generative models and produce more informed and relevant outputs.

Afternoon Session (13:30 – 17:00)

Predictive Maintenance & Time Series Anomaly Detection with Darts

Are you tired of reactive maintenance? Do you want to learn how to predict equipment failures before they happen? Detect abnormal patterns in your time series? Join our hands-on workshop on predictive maintenance and anomaly detection using Darts – the open source library for time series forecasting and anomaly detection (Python). In this workshop, you will learn how to use time series data to predict equipment failures and detect anomalies. First, we cover the basics of time series forecasting, from data preprocessing & feature engineering to model selection. Then, we move to two real-world use cases from the healthcare and industrial sectors. By the end, you will have a good understanding of how to perform both time series forecasting and anomaly detection for predictive maintenance and other applications. This workshop is suitable for data scientists, machine learning engineers, and anyone interested in time series analysis. Basic knowledge of Python is recommended.

Morning Session (09:00 – 12:30)

Unlocking the Power of LLMs: from Prompt Engineering to Agents

Unlock the full potential of large language models! Dive into the art of Prompt Engineering to harness the power of ChatGPT in boosting productivity across domains by employing various strategies. For instance, ChatGPT as a programming assistant, how to use it in automation activities and speed up daily office’s activities. We will then journey into the secret lives of LLM Agents, overcoming data limitations through the use of external tools and services. This part of the hands-on will be dedicated to a detective-themed puzzle/case designed to perform a simple Extract-Transform-Load (ETL) operation with multi-modal inputs through simple text prompts by connecting the agents to Azure Cognitive Services. The hands-on sessions will cater to both technical and non-technical participants.

Afternoon Session (13:30 – 17:00)

Building Agile Data Foundations for Data Mesh & Generative AI

Our workshop, “Building Agile Data Foundations for Data Mesh & Generative AI,” is designed to provide participants with the skills necessary for implementing Data Mesh and leveraging GenAI. Centered around the Data Vault 2.0 methodology, it teaches a flexible and scalable approach to data modeling, essential for adapting to the evolving needs of GenAI and Data Mesh frameworks. This approach is not only crucial for managing complex data systems but also for powering robust and safe LLM applications. While the concepts are demonstrated on Google Cloud Platform, they are applicable across various cloud platforms, underscoring the versatility of Data Vault 2.0. Participants will also gain practical experience with dbt (data build tool), learning to create agile, maintainable data transformations. This workshop equips attendees with the knowledge to effectively manage complex data systems and develop powerful LLM applications, crucial for thriving in a data-driven future.

Morning Session (09:00 – 12:30)

Real World Applications of LLMs for Business and Industry

This workshop aims to delve into the real-world applications of Large Language Models (LLMs), targeting both technical and business professionals. The agenda includes a balanced mix of hands-on coding and brainstorming sessions to apply LLMs in addressing modern business challenges. Participants will start with a comprehensive introduction to LLMs, understand a real business case, and then move into developing a web application using LLMs. Subsequent sessions focus on performance and cost analysis, optimizing solutions, and exploring various applications. By the end, attendees will gain practical skills and strategies for using LLMs efficiently in diverse scenarios.

Afternoon Session (13:30 – 17:00)

A Hands-on Exploration of the OpenAI API

This workshop provides a valuable resource for individuals and companies aiming to optimize their workflows by strategically integrating natural language processing (NLP) capabilities into their data infrastructure. Participants can benefit from real-world applications and understand how to practically integrate OpenAI API to address their industry-specific challenges. Additionally, important subjects such as regulatory considerations and prompt engineering optimization techniques will be touched on to ensure efficient usage of the API. All skills learned are transferable to the usage of Azure OpenAI which provides stricter company and geographical boundaries.

Morning Session (09:00 – 12:30)

Next-Gen Cleantech Solutions: Mining Insights from Media and Patent Data with Natural Language Processing (NLP) and Large Language Models (LLMs)

At a time when tackling environmental challenges is of paramount importance, the cleantech industry plays a central role in promoting sustainable solutions. However, technological innovation in the cleantech sector requires a deep understanding not only of the technologies, but also of the market requirements. This information is usually embedded in a large amount of patent and media data, which is difficult to analyze manually to effectively capture the development trend. Using Natural Language Processing (NLP) and the latest advancements in Large Language Models (LLMs) is a natural choice to accelerate innovation. In this workshop, we will share our insights gained in solving this task. Several presentations on various relevant topics will be offered, followed by a hands-on session where participants can try out our LLMs-powered cleantech question-answering and recommendation system.

Afternoon Session (13:30 – 17:00)

Grow your ML Garden on Google Cloud

“Grow Your ML Garden on Google Cloud” is a hands-on workshop that invites attendees to delve into the world of Machine Learning Operations (MLOps) using Google Cloud Platform (GCP) as a fertile ground for AI development. This workshop will guide participants through the lifecycle of ML projects – from preparing the initial data soil to nurturing and cultivating robust ML models. Emphasizing on MLOps practices, this workshop covers three key areas: preparing the data in a BigQuery’s feature store, developing ML models with Vertex AI, and managing a sustainable MLOps environment using Vertex AI Pipelines. The participants will have the opportunity to predict outages of wind turbines using a real world dataset with time series data.

Morning Session (09:00 – 12:30)

Fair ML – the challenges and opportunities of integrating fairness into machine learning applications

Ethics and fairness of Machine Learning applications are becoming increasingly important in the world of Data Science. Widespread use of ML applications, such as recommendation systems or large language models call for methods that ensure that they comply with ethical standards and policies. This workshop offers the chance to experience hands-on how to deal with biased data leading to biased models. We will highlight both the challenges of incorporating fairness into ML applications, as well as the opportunities that modern fairness tools offer in removing bias. This workshop targets ML practitioners and executives alike as incorporating fairness is both a technological as well as a societal challenge.

Afternoon Session (13:30 – 17:00)

Tutorial: Fostering Integrity in AI – Embracing Ethical Principles and Explainability

Artificial Intelligence (AI) is rapidly transforming our world, offering tremendous potential to improve efficiency, productivity, and decision-making across various industries. However, AI systems’ increasing complexity and pervasiveness raise concerns about their ethical implications and the need for transparency. This tutorial will provide a comprehensive overview of the principles and practices for fostering integrity in AI development and deployment. The tutorial will consist of five presentations, a practical hands-on session, and a panel discussion with experts from industry and academia.

Morning Session (09:00 – 12:30)

Fair and Socially Acceptable AI in HR Management

In this workshop, we will look into the consequences of the European Union’s AI Act for the use of AI in HR practices, such as recruitment, selection, training, and promotion. Organizations increasingly rely on algorithms to increase the efficiency of their HR processes. For example, algorithms are used for advertising jobs to potential candidates on social media platforms, conversing with job applicants, analyzing video recordings of job interviews, suggesting training to employees, or pre-screening job candidates’ curriculum vitae. We will discuss how organizations can design their algorithm-based HR practices in a fair and socially acceptable way.

Afternoon Session (13:30 – 17:00)

AI Standards: Navigating Compliance and Regulation for Responsible AI

AI-related standards are a key element to comply with upcoming regulation of AI. This workshop will provide an overview of the regulation process and important standards for AI innovation, and provide practical exercises on how to apply them in practice.

Morning Session (09:00 – 12:30)

Elevating Business through Social Values – The Companies’ Perspective and Future Challenges

Sustainable business practices focus on considering the impact on the environment, society, and the economy. While economic and ecological sustainability are already firmly anchored in practice, the social dimension of sustainability tends to be neglected. On the one hand, the spectrum of social outcomes is very broad and covers various areas such as diversity, inclusion, transparency and working atmosphere. On the other hand, there are various data-driven support services available to foster these outcomes potentially, but a link between them is missing. It is therefore becoming increasingly important for companies to focus on social values. They should understand the causal relationship between data-driven operations and social outcomes, improve them, and promote their social commitment.