Ga verder naar de inhoud
Training

Anomaly Detection and Explainability for Time-Series Data

22 jun. 2026 13:00 - 16:30

As AI systems are increasingly used to monitor complex, time-dependent processes, understanding anomalies and their underlying causes becomes critical. This hands-on course introduces participants to anomaly detection and explainable AI (xAI) techniques for both transactional and time-series data, combining practical modeling with interpretable insights.

Lees meer & inschrijven ⇗

Praktische info:

22 jun. 2026 13:00 - 16:30
3,5 uur
Online
Engels
Doelgroep: Everyone who wants to get a deeper understanding of how and why AI systems make decisions

Inschrijven?

  • Voorwaarden: Familiarity with basic machine learning concepts and Python programming
  • Prijs: Free of charge for all participants from academia, industry, and public administration from EU and/or EuroHPC JU member countries
Lees meer & inschrijven ⇗

georganiseerd door:

This hands-on training introduces explainable AI (xAI) for anomaly detection in both tabular and time series data. Participants work with real-world datasets, including credit card fraud and NYC taxi demand, using standard machine learning models and SHAP-based explanations. The session covers the full workflow from data exploration to model interpretation. Special attention is given to challenges such as class imbalance and temporal dependencies. The course concludes with a critical discussion of limitations and best practices for applying xAI in practice for timeseries anomaly detection.
 

Learning Outcomes: 

  • Understand typical use cases of anomaly detection and explainability for transactional and time-series data
  • Perform exploratory data analysis and apply suitable anomaly detection techniques
  • Build and evaluate models for anomaly detection in tabular and time-series settings
  • Apply and interpret explainability methods (e.g., feature importance, SHAP)
  • Recognize challenges such as class imbalance and temporal dependencies and account for them in practice
  • Critically assess the limitations and risks of explainability methods in real-world applications

Gerelateerde opleidingen