Regular Inference on Artificial Neural Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Regular Inference on Artificial Neural Networks

Franz Mayr
  • Function : Author
  • PersonId : 1043684
Sergio Yovine
  • Function : Author
  • PersonId : 1043685


This paper explores the general problem of explaining the behavior of artificial neural networks (ANN). The goal is to construct a representation which enhances human understanding of an ANN as a sequence classifier, with the purpose of providing insight on the rationale behind the classification of a sequence as positive or negative, but also to enable performing further analyses, such as automata-theoretic formal verification. In particular, a probabilistic algorithm for constructing a deterministic finite automaton which is approximately correct with respect to an artificial neural network is proposed.

Dates and versions

hal-02998138 , version 1 (10-11-2020)





Franz Mayr, Sergio Yovine. Regular Inference on Artificial Neural Networks. 2nd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2018, Hamburg, Germany. pp.350-369, ⟨10.1007/978-3-319-99740-7_25⟩. ⟨hal-02998138⟩
8 View
0 Download



Gmail Facebook X LinkedIn More