Topological explanations of deep neural networks

Rabiza, M. (2026)

Article / Letter to editor

Recent philosophical work on explainable AI has explored mechanistic methods targeting the causal structure of deep neural networks. However, the ever-growing complexity of deep learning models challenges purely decompositional strategies. This paper advances an alternative perspective based on topological explanations—an approach that both complements and, in some respects, surpasses the mechanistic perspective. By examining how topological properties of deep neural networks relate to model behavior in a non-causal, abstract, and counterfactual manner, I argue that this framework is particularly well suited to addressing why-questions in AI contexts. Drawing on cases of model-driven and data-driven explanations, I show that the topological explanatory strategy offers distinctive epistemic advantages for explainability research.

• Topological explanation
• Deep neural networks
• Explainable artificial intelligence

• All authors: Rabiza, M.
• Date: 2026-07-10
• Journal: Synthese
• Volume: 208
• Advanced Publication: Yes
• DOI: doi:10.1007/s11229-026-05646-2
• Link: https://doi.org/10.1007/s11229-026-05646-2