Short Trainings & Workshops

This workshop introduces a comprehensive framework for causal analysis, enabling participants to understand and model cause-effect relationships across domains, such as medicine (e.g., clinical trials), retail (e.g. customer engagement), economics (e.g., policy evaluation), and technology (e.g., recommendation systems).

‍

We begin by examining the limitations of predictive models and correlations, highlighting why they are often insufficient for answering “what if” questions or reasoning about interventions. To overcome these challenges and avoid common pitfalls, we present the foundations of causal reasoning, including counterfactuals, interventions, and causal graphs, and demonstrate how these concepts apply to real-world problems.

‍

The workshop is structured around two core areas: causal discovery and causal inference. Causal discovery focuses on uncovering underlying causal structures directly from data. We will explore a range of methods, with particular attention to their assumptions and limitations. Causal inference, in contrast, aims to estimate the effect of interventions or treatments on outcomes. We will cover both quasi-experimental approaches and modern machine learning techniques, along with practical strategies for evaluating their validity.

‍

Finally, two extended hands-on sessions will allow participants to apply these theoretical concepts in practice and quickly get started with causal machine learning using Python.

This hands-on workshop provides a deep dive into advanced AI techniques, focusing on structured outputs from Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Multimodal AI. Participants will engage in practical exercises to refine LLM outputs, apply advanced RAG methods to medical texts, and explore agentic AI concepts using Hugging Face libraries. Ideal for those looking to enhance their AI workflows with cutting-edge methodologies.

Bias mitigation techniques can be used to ensure fairness and impartiality in the outcomes of machine learning models, using robust data collection, preprocessing, in-processing, and post-processing methods. In this seminar, we will present the most popular techniques, and we will show some examples of their application.

This workshop provides an overview of techniques to model and predict propensity, namely the probability that a person will perform a given action in the future, based on past observations. It includes time-window classification and survival analysis, as well as customer lifetime value and causal analysis.

This workshop provides a general introduction to computer vision. It covers typical tasks where computer vision algorithms are employed, elaborationg on the basic principles and how to implement solutions (libraries, data prep, best practices,…). Such tasks include supervised and non-supervised learning (image recognition, object detection), transfer learning and diffusion models. At the end of the course we present a concrete use case from a company that uses computer vision to map & track marine plastic.

This workshop provides a high level overview of MLOps, focusing on the deployment of proof-of-concept AI solutions. We will introduce basic MLOps concepts and best practices, and present business use cases and corresponding specific recommendations.

This course offers an introduction to the recent developments of the Large Language Models. After a high level introduction about transformers, the course focus on LLMs and its applications. A special attention is given to ChatGPT and to the RLHF technique. The second part of the course is dedicated to a hands-on session (in Renku or Google Collaboratory) with examples and exercises on how to use models and libraries in Huggingface.

In this seminar the participants will learn what time series data is and its real-world applications. We will review time series key concepts, decomposition and the most popular forecasting methods. We will also explore clustering methods specifically designed for time series and we will conclude with some real world applications of time series analysis.