City Research Online

Abstract

This paper proposes an algorithm to extract a Weighted Finite Automaton (WFA) from a Recurrent Neural Network (RNN), by adapting the algorithm in combination with spectral learning using Singular Value Decomposition (SVD). The method introduces a discrete abstraction of the RNN’s hidden state space to enable approximate equivalence queries within the framework. Through these queries, counterexamples are identified and used to iteratively refine the prefix and suffix sets that define the Hankel matrix, thereby improving the accuracy of successive WFA hypotheses. This work lays the groundwork for integrating discrete clustering with spectral learning in the context of WFA extraction from RNNs, an area that remains underexplored, with potential applications in sequence modelling and analysis. Future work will focus on implementing and empirically validating the proposed approach.

Publication Type:	Conference or Workshop Item (Paper)
Additional Information:	© 2025 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Publisher Keywords:	Recurrent Neural Networks, Weighted Finite Automata, Explainable AI, Interpretability
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments:	School of Science & Technology School of Science & Technology > Department of Computer Science
SWORD Depositor:	Symplectic Administrator

Export

Downloads