Foundations of Interpretable Deep Learning

Material

You can find our tutorial slides here (pdf).

The first part of our talk was inspired by our position paper on “Symmetries of Interpretable Models”.

A recording of our presentation can be found here (video).

For a complete bibliography of the topics and works discussed in this tutorial, please refer to our resources section.

Schedule

Below is the expected (rough) schedule for this tutorial where we indicate next to each section who will be presenting that section’s material (PB for “Pietro Barbiero” and MEZ for “Mateo Espinosa Zarlenga”).

Required Background

Our material will assume a basic knowledge of ML (e.g., foundations of supervised learning, experimental design, basic probabilistic modelling, etc.), with particular emphasis on a solid Deep Learning foundation (e.g., tensor calculus, neural networks, backpropagation, etc.). Concepts that may require mathematical tools/expertise beyond those one would expect to be shared among the AAAI community will be (re)introduced in our tutorial.

Presenters

Mateo Espinosa Zarlenga

University of Oxford, UK

Pietro Barbiero

IBM Research, Switzerland

Citing This Tutorial

If you found this tutorial useful for your research, blogs, or work, please cite it as follows:

Barbiero P. and Espinosa Zarlenga M. (2026). Foundations of Interpretable Deep Learning. Tutorial at the Fortieth Annual AAAI Conference on Artificial Intelligence (AAAI). https://interpretabledeeplearning.github.io/

Or use the following bibtex entry:

@misc{interpretabledl2026tutorial,
  title        = {Tutorial on Foundations of Interpretable Deep Learning (AAAI-2026)},
  author       = {Barbiero, P. and Espinosa Zarlenga, M.},
  year         = {2026},
  howpublished = {Tutorial at the Fortieth Annual AAAI Conference on Artificial Intelligence (AAAI)},
  url          = {https://interpretabledeeplearning.github.io/}
}