Property Checking with Interpretable Error Characterization for Recurrent Neural Networks

This paper presents a novel on-the-fly, black-box, property-checking through learning approach as a means for verifying requirements of recurrent neural networks (RNN) in the context of sequence classification. Our technique steps on a tool for learning probably approximately correct (PAC) determini...

Full description

Bibliographic Details

Main Author:	Mayr, Franz (author)
Other Authors:	Yovine, Sergio (author), Visca, Ramiro (author)
Format:	article
Language:	English
Published:	2021
Subjects:	Recurrent neural networks Probably approximately correct learning Black-box explainability Ciencias Naturales y Exactas Ciencias de la Computación e Información
Online Access:	https://hdl.handle.net/20.500.12381/457 https://doi.org/10.3390/make3010010
Tags:	Add Tag No Tags, Be the first to tag this record!