This chapter surveys the recent advancements on the extension of Reservoir Computing toward deep architectures, which is gaining increasing research attention in the neural networks community. Within this context, we focus on describing the major features of Deep Echo State Networks based on the hierarchical composition of multiple reservoirs. The intent is to provide a useful reference to guide applications and further developments of this efficient and effective class of approaches to deal with times-series and more complex data within a unified description and analysis.
Deep Reservoir Computing
Gallicchio C.
;Micheli A.
2021-01-01
Abstract
This chapter surveys the recent advancements on the extension of Reservoir Computing toward deep architectures, which is gaining increasing research attention in the neural networks community. Within this context, we focus on describing the major features of Deep Echo State Networks based on the hierarchical composition of multiple reservoirs. The intent is to provide a useful reference to guide applications and further developments of this efficient and effective class of approaches to deal with times-series and more complex data within a unified description and analysis.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
