%0 Conference Proceedings
%T On-the-fly Black-Box Probably Approximately Correct Checking of Recurrent Neural Networks
%+ Universidad ORT Uruguay
%A Mayr, Franz
%A Visca, Ramiro
%A Yovine, Sergio
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 4th International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE)
%C Dublin, Ireland
%Y Andreas Holzinger
%Y Peter Kieseberg
%Y A Min Tjoa
%Y Edgar Weippl
%I Springer International Publishing
%3 Machine Learning and Knowledge Extraction
%V LNCS-12279
%P 343-363
%8 2020-08-25
%D 2020
%R 10.1007/978-3-030-57321-8_19
%Z Computer Science [cs]
%Z Humanities and Social Sciences/Library and information sciencesConference papers
%X We propose a procedure for checking properties of recurrent neural networks used for language modeling and sequence classification. Our approach is a case of black-box checking based on learning a probably approximately correct, regular approximation of the intersection of the language of the black-box (the network) with the complement of the property to be checked, without explicitly building individual representations of them. When the algorithm returns an empty language, there is a proven upper bound on the probability of the network not verifying the requirement. When the returned language is nonempty, it is certain the network does not satisfy the property. In this case, an explicit and interpretable characterization of the error is output together with sequences of the network truly violating the property. Besides, our approach does not require resorting to an external decision procedure for verification nor fixing a specific property specification formalism.
%G English
%Z TC 5
%Z TC 8
%Z TC 12
%Z WG 8.4
%Z WG 8.9
%Z WG 12.9
%2 https://inria.hal.science/hal-03414742/document
%2 https://inria.hal.science/hal-03414742/file/497121_1_En_19_Chapter.pdf
%L hal-03414742
%U https://inria.hal.science/hal-03414742
%~ SHS
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-WG
%~ IFIP-TC12
%~ IFIP-TC8
%~ IFIP-WG8-4
%~ IFIP-WG8-9
%~ IFIP-CD-MAKE
%~ IFIP-WG12-9
%~ IFIP-LNCS-12279