Identification of Discrete Event Systems Using the Compound Recurrent Neural Network: Extracting DEVS from Trained Network

DOI10.1177/0037549702078002210MaRDI QIDQ3148237zbMATH OpenOpenAlexFDO

Authors Si Jong Choi, T. G. Kim

Publication date 2002

Published in SIMULATION (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1177/0037549702078002210

zbMATH Keywords

model minimizationDEVS formalismmodel extraction

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Nonlinear system identification using discrete-time recurrent neural networks with stable learning algorithms.
• Discrete-time recurrent high order neural networks for nonlinear identification
• Dynamic system identification via recurrent multilayer perceptrons
• On the adaptation of recurrent neural networks for system identification
• A new recurrent neurofuzzy network for identification of dynamic systems
• Identifiability of recurrent neural networks
• Recurrent neural networks coupled with linear systems: Observability in continuous and discrete time

Cites work

• scientific article; zbMATH DE number 3664335 (Why is no real title available?)
• scientific article; zbMATH DE number 3717206 (Why is no real title available?)
• scientific article; zbMATH DE number 51537 (Why is no real title available?)
• scientific article; zbMATH DE number 3598362 (Why is no real title available?)
• Supervisory control of timed discrete-event systems

This page was built for publication: Identification of Discrete Event Systems Using the Compound Recurrent Neural Network: Extracting DEVS from Trained Network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3148237)