We introduce a novel constructive algorithm which progressively builds the architecture of GraphESN, which generalizes Reservoir Computing to learning in graph domains. Exploiting output feedback signals in a forward fashion in such construction, allows us to introduce supervision in the reservoir encoding process. The potentiality of the proposed approach is experimentally assessed on real-world tasks from Toxicology.
Constructive Reservoir Computation with Output Feedbacks for Structured Domains
GALLICCHIO, CLAUDIO;MICHELI, ALESSIO;
2012-01-01
Abstract
We introduce a novel constructive algorithm which progressively builds the architecture of GraphESN, which generalizes Reservoir Computing to learning in graph domains. Exploiting output feedback signals in a forward fashion in such construction, allows us to introduce supervision in the reservoir encoding process. The potentiality of the proposed approach is experimentally assessed on real-world tasks from Toxicology.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.
