This is an interim version of our Electronic Legal Deposit Catalogue-eJournals and eBooks while we continue to recover from a cyber-attack.
A novel Deep Neural Network architecture for non-linear system identification⁎This project was partially supported by the Italian Ministry of University and Research under the PRIN'17 project "Data-driven learning of constrained control systems", contract no. 2017J89ARP and by NVIDIA Corporation trough the GPU Grant Program. Issue 7 (2021)
Record Type:
Journal Article
Title:
A novel Deep Neural Network architecture for non-linear system identification⁎This project was partially supported by the Italian Ministry of University and Research under the PRIN'17 project "Data-driven learning of constrained control systems", contract no. 2017J89ARP and by NVIDIA Corporation trough the GPU Grant Program. Issue 7 (2021)
Main Title:
A novel Deep Neural Network architecture for non-linear system identification⁎This project was partially supported by the Italian Ministry of University and Research under the PRIN'17 project "Data-driven learning of constrained control systems", contract no. 2017J89ARP and by NVIDIA Corporation trough the GPU Grant Program.
Abstract: We present a novel Deep Neural Network (DNN) architecture for non-linear system identification. We foster generalization by constraining DNN representational power. To do so, inspired by fading memory systems, we introduce inductive bias (on the architecture) and regularization (on the loss function). This architecture allows for automatic complexity selection based solely on available data, in this way the number of hyper-parameters that must be chosen by the user is reduced. Exploiting the highly parallelizable DNN framework (based on Stochastic optimization methods) we successfully apply our method to large scale datasets.