Neural Symbolic Interpretability

Add to your list(s) Download to your calendar using vCal

• Pietro Barbiero (IBM Zurich)
• Thursday 12 February 2026, 16:00-17:00
• Lecture Theatre 2, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Mateja Jamnik.

Notice unusual day and time

Neuro-symbolic (NeSy) interpretability provides a formal language for controlling deep neural networks (DNNs) and ensuring that their behavior satisfies human desiderata. We will present the architectural conditions that enable NeSy control in DNNs and, based on these conditions, introduce a general blueprint for instantiating NeSy-interpretable reasoners. We illustrate this paradigm using two representative examples: verifiable and causally transparent concept-based models.

Pietro is a Swiss Postdoctoral Fellow and Ellis member at IBM Research. Previously, he was a postdoc at Universita’ della Svizzera Italiana and received his PhD at the University of Cambridge. His research focuses on the mathematical foundations of interpretability and on developing causally transparent models to go beyond the current accuracy-interpretability trade-off.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Artificial Intelligence Research Group Talks (Computer Laboratory)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Guy Emerson's list
• Hanchen DaDaDash
• Interested Talks
• Lecture Theatre 2, Computer Laboratory, William Gates Building
• Martin's interesting talks
• PhD related
• School of Technology
• Speech Seminars
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• rp587
• yk373's list
• yk449

Note that ex-directory lists are not shown.