The nonlinear transformation used in reservoir computing can be effectively replaced by nonlinear vector autoregression (NVAR) for data prediction. In such a method, also known as next generation reservoir computing (NGRC), the input signal consists of a linear part, including several previous data points, and their nonlinear combinations. Here we show that the application of this method to a network with memristive weights (memristors) can be used to predict signals, depending on the nature of the nonlinear functions and the number of memristors. The network allows an accurate prediction of chaotic time series of Mackey-Glass and Duffing oscillators
Next Generation Memristor Reservoir Computing / Nikiruy, K.; Ivanov, T.; Ziegler, M.; Rossetti, D.; Corinto, F.; Ascoli, A.; Tetzlaff, R.; Demirkol, A. S.; Schmitt, N.. - (2024), pp. 912-917. (Intervento presentato al convegno 2024 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) tenutosi a St Albans (UK) nel 21-23 October 2024) [10.1109/metroxraine62247.2024.10796786].
Next Generation Memristor Reservoir Computing
Rossetti, D.;Corinto, F.;Ascoli, A.;Tetzlaff, R.;
2024
Abstract
The nonlinear transformation used in reservoir computing can be effectively replaced by nonlinear vector autoregression (NVAR) for data prediction. In such a method, also known as next generation reservoir computing (NGRC), the input signal consists of a linear part, including several previous data points, and their nonlinear combinations. Here we show that the application of this method to a network with memristive weights (memristors) can be used to predict signals, depending on the nature of the nonlinear functions and the number of memristors. The network allows an accurate prediction of chaotic time series of Mackey-Glass and Duffing oscillatorsFile | Dimensione | Formato | |
---|---|---|---|
Next_Generation_Memristor_Reservoir_Computing (1).pdf
accesso riservato
Descrizione: Paper NGMRC pubblicato a convegno
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
1.16 MB
Formato
Adobe PDF
|
1.16 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Memristor_ngrc_fin_rev (2).pdf
accesso aperto
Descrizione: Paper pre-pubblicazione
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
695.25 kB
Formato
Adobe PDF
|
695.25 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2996958