Generalised Geometric Logic: A Logic for Expressing Neural Network Architectures

Ramit Das and Purbita Jana ()
Additional contact information
Ramit Das: Cadence
Purbita Jana: Assistant Professor and Chair of M.Sc. Data Science Programme, Madras School of Economics, Chennai, India.

Working Papers from Madras School of Economics,Chennai,India

Abstract: Neural networks achieve strong empirical performance, yet their architectural semantics and compositional structure remain difficult to analyse formally. This paper develops a logical–topological framework for reasoning about neural network architectures independently of learning dynamics. Focusing on the ART/LAPART family as a canonical testbed in which bidirectional interaction and stability are ex-plicit, we provide a semantic interpretation of excitation relations using geometric logic and topological systems. We extend the classical setting to fuzzy and frame-valued semantics in order to capture graded and potentially incomparable activation strengths. With this extension we show that we express SHAP - a Neural Network Explainability methodology. The contribution is foundational: it clarifies how ar-chitectural causal structure can be represented, compared, and composed. While the technical development centres on ART and LAPART, the framework isolates structural principles—compositionality, graded influence, and continuity—that can be extend to modern deep neural network architectures.

Keywords: Geometric logic; Topological systems; Neural network semantics; Adaptive Resonance Theory; LAPART; Fuzzy topology; Explainable AI; SHAP values; Frame-valued semantics; Neural architectures (search for similar items in EconPapers)
JEL-codes: C02 C45 C63 C65 D83 (search for similar items in EconPapers)
Pages: 23 pages
Date: 2026-05
References: Add references at CitEc
Citations:

Downloads: (external link)
https://mse.ac.in/wp-content/uploads/2026/05/Working-paper-300.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:mad:wpaper:2026-300

Access Statistics for this paper

More papers in Working Papers from Madras School of Economics,Chennai,India Contact information at EDIRC.
Bibliographic data for series maintained by Geetha G ().