DRASiW is an extension of the WiSARD Weightless NN model with the capability of storing the frequencies of seen patterns during the training stage in an internal data structure called "mental image" (MI). Due to these capability, in previous work it was demonstrated how to reversely process MIs in order to generate synthetic prototypes from training samples. In this paper we show how DRASiW-like systems are able to transfer memory between different architectures while preserving the same functionalities.
Memory transfer in DRASiW-like systems
De Gregorio Massimo;Giordano Maurizio
2015
Abstract
DRASiW is an extension of the WiSARD Weightless NN model with the capability of storing the frequencies of seen patterns during the training stage in an internal data structure called "mental image" (MI). Due to these capability, in previous work it was demonstrated how to reversely process MIs in order to generate synthetic prototypes from training samples. In this paper we show how DRASiW-like systems are able to transfer memory between different architectures while preserving the same functionalities.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.
