The Social and Smart (SandS) project aims to lay the foundations for a social network of home appliance users endowed with a layer of intelligent systems that must be able to produce new solutions to new problems on the basis of the knowledge accumulated by the social network players. The system is not a simple recollection of tested appliance use recipes, but it will have the ability generate new or refine existing recipes trying to satisfy user demands, and to perform fine tuning of recipes on the basis of user satisfaction by a hidden reinforcement learning process. This paper aims to advance on the specification of diverse aspects and roles of the system architecture, to get a clearer picture of module interactions and duties, along with data transfer and transformation paths.

Social and smart : towards an instance of subconscious social intelligence / B. Apolloni, M. Fiasché, G. Galliani, C. Zizzo, G. Caridakis, G. Siolas, S. Kollias, M. Graña, F. Barrientos (COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE). - In: EANN : Engineering Applications of Neural Networks[s.l] : Springer, 2013. - ISBN 978-3-642-41015-4. - pp. 302-311 (( Intervento presentato al 14. convegno International Conference on Engineering Applications of Neural Networks (EANN) : September, 13th - 16th tenutosi a Halkidiki (Greece) nel 2013 [10.1007/978-3-642-41016-1_32].

Social and smart : towards an instance of subconscious social intelligence

B. Apolloni
Primo
;
M. Fiasché
Secondo
;
2013

Abstract

The Social and Smart (SandS) project aims to lay the foundations for a social network of home appliance users endowed with a layer of intelligent systems that must be able to produce new solutions to new problems on the basis of the knowledge accumulated by the social network players. The system is not a simple recollection of tested appliance use recipes, but it will have the ability generate new or refine existing recipes trying to satisfy user demands, and to perform fine tuning of recipes on the basis of user satisfaction by a hidden reinforcement learning process. This paper aims to advance on the specification of diverse aspects and roles of the system architecture, to get a clearer picture of module interactions and duties, along with data transfer and transformation paths.
Settore INF/01 - Informatica
2013
Book Part (author)
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/256946
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 5
social impact