Zobrazeno 1 - 10
of 151
pro vyhledávání: '"Saitta, Lorenza"'
Publikováno v:
Intelligenza Artificiale. 2018, Vol. 12 Issue 1, p19-22. 4p.
Autor:
Saitta, Lorenza1
Publikováno v:
Intelligenza Artificiale. 2014, Vol. 8 Issue 1, p3-22. 20p.
Autor:
Saitta, Lorenza
Publikováno v:
Philosophical Transactions: Biological Sciences, 2003 Jul . 358(1435), 1173-1173.
Externí odkaz:
https://www.jstor.org/stable/3558207
Autor:
Saitta, Lorenza, Zucker, Jean-Daniel
Publikováno v:
Applied Artificial Intelligence. Sep2001, Vol. 15 Issue 8, p761. 16p. 5 Diagrams.
Autor:
Neri, Filippo, Saitta, Lorenza
Publikováno v:
Evolutionary Computation. Spring96, Vol. 4 Issue 1, p87. 21p. 1 Diagram, 6 Graphs.
Autor:
Console, Luca, Magro, Diego, Micalizio, Roberto, Scala, Enrico, Theseider Dupré, Daniele, Torta, Gianluca, Martelli, Alberto, Saitta, Lorenza
Publikováno v:
Intelligenza Artificiale; 2018, Vol. 12 Issue 1, p31-40, 10p
Publikováno v:
Intelligenza Artificiale; 2018, Vol. 12 Issue 1, p41-44, 4p
Publikováno v:
Intelligenza Artificiale; 2018, Vol. 12 Issue 1, p23-29, 7p
Publikováno v:
Cambridge University Press, 2011, 978-0521763912
International audience; Phase transitions typically occur in combinatorial computational problems and have important consequences, especially with the current spread of statistical relational learning as well as sequence learning methodologies. In Ph
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f10a841fc1db63f95e25369640c9ab31
https://hal.archives-ouvertes.fr/hal-02480265
https://hal.archives-ouvertes.fr/hal-02480265
Autor:
Saitta, Lorenza, Vrain, Christel
Publikováno v:
AAAI Technical Report
WARA-2010, AAAI-10 Workshop on Abstraction, Reformulation, and Approximation
WARA-2010, AAAI-10 Workshop on Abstraction, Reformulation, and Approximation, Jul 2010, Atlanta, United States
WARA-2010, AAAI-10 Workshop on Abstraction, Reformulation, and Approximation
WARA-2010, AAAI-10 Workshop on Abstraction, Reformulation, and Approximation, Jul 2010, Atlanta, United States
International audience; In this paper we describe a preliminary investigation on the use of abstraction operators to reduce the complexity of inference in Markov Networks. More specifically, we are interested in Logic Markov Network, where the use of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::275951795e9e84fb2e1e2b8798dd0006
https://hal.archives-ouvertes.fr/hal-00484619
https://hal.archives-ouvertes.fr/hal-00484619