Łukasiewicz Logic with Actions for Neural Networks training
Based on the already known connection between multilayer perceptrons and ukasiewicz logic with rational coefficients, we take a step forward in analyzing its training process using a three-sorted hybrid modal logic: a multilayer perceptron is a logical formula; the actions of the training process are modal operators; the training process is a sequence of logical deductions.Using the proof assistant and the programming language Lean 4, the algorithmic implementation of the training process is certified by logical proofs.
Authors
- Ioana Leuştean (ORCID: https://orcid.org/0000-0002-1884-6456)
- Bogdan Macovei
Institutions
- University of Bucharest (RO)
Publication Details
- Journal
- Electronic Proceedings in Theoretical Computer Science
- Published
- 2025-09-15
- DOI
- https://doi.org/10.4204/eptcs.427.4
- Citations
- 2
- Primary Topic
- Neural Networks and Applications
- Type
- article
- Field-Weighted Citation Impact
- 4.96