Exploring methods to understand deep learning models.

What We Do

We are a community of researchers interested in Interpretable Deep Learning (IDL). We organize tutorials, reading groups, and open resources to foster deeper understanding and stronger collaboration across the field.

📚
Reading Group

Join regular discussions on the latest interpretability research.
🎓
Tutorials

Learn from in-depth tutorials on interpretable deep learning.
📖
Resources

Explore curated papers, tools, and community materials.
💬
Slack Channel

Connect with researchers and practitioners in the community.
✉️
Mailing List

Stay updated with announcements, sessions, and events.

About Us

Aya Abdelsalam Ismail
Aya Abdelsalam Ismail

Co-Founder and CSO of Guide Labs, US
Pietro Barbiero
Pietro Barbiero

Postdoc Fellow at IBM Research, Switzerland
Mateo Espinosa Zarlenga
Mateo Espinosa Zarlenga

Postdoc Fellow at University of Oxford, UK
Giuseppe Marra
Giuseppe Marra

Professor at KU Leuven, BE
Alberto Termine
Alberto Termine

Researcher IDSIA USI-SUPSI, CH

Contact

For questions, please contact Mateo at mateo.espinosazarlenga@trinity.ox.uk or Pietro at pietro.barbiero@ibm.com.