This course will take place as an online event. The link to the online platform will be provided to the accepted registrants only.
Join our comprehensive course to embark on an instructive journey into the world of eXplainable AI (XAI). Throughout the course, participants will develop a solid foundational understanding of XAI, primarily emphasizing how XAI methodologies can expose latent
biases in datasets and reveal valuable insights.
The course starts with a broad overview of XAI, setting the stage for a deep dive into cutting-edge model-agnostic interpretation techniques. As the course progresses, we shift our focus to model-specific post-hoc interpretation methods. Through immersive training, participants will learn to interpret machine learning algorithms and unravel the intricacies of deep neural networks, such as convolutional neural networks (CNN) and transformers. They will also become skilled in applying these techniques to various data formats, encompassing tabular data, images, and 1D data.
In addition to theoretical insights, participants will engage in hands-on practical sessions to apply these techniques effectively.
Take advantage of this opportunity to enhance your expertise in XAI and acquire the skills needed to navigate the intricate landscape of AI interpretability. Enroll now and unlock the potential of XAI!
The registration form is set for online courses. Adjust maximum number of participants if necessary.
Learning outcome:
- Gain an appreciation for the significance of XAI.
- Explore the available model-agnostic and model-specific XAI methodologies.
- Acquire the skills to interpret the results and visualizations of these methodologies through practical exercises.
- Master the skill of applying XAI techniques to diverse data types, including tabular data, images, and 1D data.
- Develop the ability to discern the most appropriate XAI method for a given task.
Prerequisites:
This course assumes you have minimal experience running Python and Machine Learning Frameworks like Tensorflow and PyTorch.
Target audience:
Master students, PhD students and Postdocs with interest in Machine Learning
Further information:
please visit the JSC webpage https://go.fzj.de/2023-explainable-dl
Instructors:
Sabrina Narimene Benassou, JSC
Dr. Donatella Cea, Helmholtz Munich
Dr. Lisa Borros de Andrade e Sousa, Helmholtz Munich
Dr. Alina Bazarova, JSC
Dr. Elisabeth Georgii, Helmholtz Munich
Francesco Campi, Helmholtz Munich
Dr. Florian Kofler, Helmholtz Munich