Imperial College London
Portrait Picture

ProfessorAlessioLomuscio

Faculty of Engineering, Department of Computing

Professor of Safe Artificial Intelligence
 
 
 
//

Contact

 

+44 (0)20 7594 8414a.lomuscio Website

 
 
//

Location

 

Imperial-XTranslation & Innovation Hub BuildingWhite City Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Akintunde:2019,
author = {Akintunde, M and Kevorchian, A and Lomuscio, A and Pirovano, E},
publisher = {Association for the Advancement of Artificial Intelligence},
title = {Verification of RNN-based neural agent-environment systems},
url = {http://hdl.handle.net/10044/1/77521},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - We introduce agent-environment systems where the agent is stateful and executing a ReLU recurrent neural network. We define and study their verification problem by providing equivalences of recurrent and feed-forward neural networks on bounded execution traces. We give a sound and complete procedure for their verification against properties specified in a simplified version of LTL on bounded executions. We present an implementation and discuss the experimental results obtained.
AU  - Akintunde,M
AU  - Kevorchian,A
AU  - Lomuscio,A
AU  - Pirovano,E
PB  - Association for the Advancement of Artificial Intelligence
PY  - 2019///
SN  - 2159-5399
TI  - Verification of RNN-based neural agent-environment systems
UR  - http://hdl.handle.net/10044/1/77521
ER  -
Download