Property Checking with Interpretable Error Characterization for Recurrent Neural Networks
Machine Learning and Knowledge Extraction, 2021 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.
Franz Mayr, Sergio Yovine, Ramiro Visca
doaj +1 more source
Horn Clauses for Communicating Timed Systems [PDF]
Electronic Proceedings in Theoretical Computer Science, 2014 Languages based on the theory of timed automata are a well established approach for modelling and analysing real-time systems, with many applications both in industrial and academic context.
Hossein Hojjat +3 more
doaj +1 more source
Partition Refinement of Component Interaction Automata: Why Structure Matters More Than Size [PDF]
Electronic Proceedings in Theoretical Computer Science, 2010 Automata-based modeling languages, like Component Interaction Automata, offer an attractive means to capture and analyze the behavioral aspects of interacting components.
Markus Lumpe, Rajesh Vasa
doaj +1 more source
Let's Learn Their Language? A Case for Planning with Automata-Network Languages from Model Checking
Proceedings of the AAAI Conference on Artificial Intelligence, 2020 It is widely known that AI planning and model checking are closely related. Compilations have been devised between various pairs of language fragments. What has barely been voiced yet, though, is the idea to let go of one's own modeling language, and use one from the other area instead.
Jörg Hoffmann 0001 +5 more
openaire +2 more sources
Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languages
, 2022 Recurrent Neural Networks (RNNs) have achieved tremendous success in sequential data processing. However, it is quite challenging to interpret and verify RNNs' behaviors directly. To this end, many efforts have been made to extract finite automata from RNNs.
Zeming Wei +2 more
openaire +2 more sources
On equations for regular languages, finite automata, and sequential networks
Theoretical Computer Science, 1980 AbstractWe consider systems of equations of the form Xi=⋃α∈A α·Fi,a∪δi i=1,…,n where A is the underlying alphabet, the Xi are variables, the Pi,a are boolean functions in the variables Xi, and each δi is either the empty word or the empty set. The symbols υ and ∪ denote concatenation and union of languages over A.
Janusz A. Brzozowski, Ernst L. Leiss
openaire +2 more sources
The SHIFT Programming Language and Run-time System for Dynamic Networks of Hybrid Automata [PDF]
, 2000 SHIFT is a programming language for describing and simulating dynamic networks of hybrid automata. Such Systems consist of components that can be created, interconnected and destroyed as the system evolves. Components exhibit hybrid behavior, consisting of continuous-time phases separated by discrete-event transitions.
Deshpande, Akash +2 more
openaire +3 more sources
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks
CoRR, 2019 15 Pages, 13 Figures, Accepted to ICLR ...
Joshua J. Michalenko +5 more
openaire +3 more sources
IEEE AccessWe present a formal and constructive framework for simulating Alternating Finite Automata (AFAs) using Logic Gated Time Shared Feedforward Networks (LG-TS-FFNs).
Sahil Rajesh Dhayalkar
doaj +1 more source
Weighted automata extraction and explanation of recurrent neural networks for natural language tasks
Journal of Logical and Algebraic Methods in ProgrammingRecurrent Neural Networks (RNNs) have achieved tremendous success in processing sequential data, yet understanding and analyzing their behaviours remains a significant challenge. To this end, many efforts have been made to extract finite automata from RNNs, which are more amenable for analysis and explanation.
Wei, Zeming +3 more
openaire +4 more sources