This paper presents a new approach to build RF dynamic behavioral models, based on time-delay neural networks (TDNNs), suitable for FET devices, and capable to identify the working class and to characterize both short- and long-term device memory, through a time-domain training procedure, for a wide range of input power levels. The presented model has been effectively applied to GaN-based devices, working in class A, AB and B.
Advanced Neural Network Techniques for GaN-HEMT Dynamic Behavior Characterization / Orengo, G.; Colantonio, P.; Giannini, F.; Pirola, Marco; Camarchia, Vittorio; DONATI GUERRIERI, Simona; Ghione, Giovanni. - STAMPA. - Unico:(2006), pp. 249-252. (Intervento presentato al convegno 2006 European Microwave Integrated Circuits Conference tenutosi a Manchester (UK) nel 10-13 September 2006) [10.1109/EMICC.2006.282799].
Advanced Neural Network Techniques for GaN-HEMT Dynamic Behavior Characterization
PIROLA, Marco;CAMARCHIA, VITTORIO;DONATI GUERRIERI, Simona;GHIONE, GIOVANNI
2006
Abstract
This paper presents a new approach to build RF dynamic behavioral models, based on time-delay neural networks (TDNNs), suitable for FET devices, and capable to identify the working class and to characterize both short- and long-term device memory, through a time-domain training procedure, for a wide range of input power levels. The presented model has been effectively applied to GaN-based devices, working in class A, AB and B.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/1707868
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo