Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Trani, Salvatore"'
Autor:
Busolin, Francesco, Lucchese, Claudio, Nardini, Franco Maria, Orlando, Salvatore, Perego, Raffaele, Trani, Salvatore
Learned dense representations are a popular family of techniques for encoding queries and documents using high-dimensional embeddings, which enable retrieval by performing approximate k nearest-neighbors search (A-kNN). A popular technique for making
Externí odkaz:
http://arxiv.org/abs/2408.04981
Quantization and pruning are two effective Deep Neural Networks model compression methods. In this paper, we propose Automatic Prune Binarization (APB), a novel compression technique combining quantization with pruning. APB enhances the representatio
Externí odkaz:
http://arxiv.org/abs/2306.08960
Autor:
Busolin, Francesco, Lucchese, Claudio, Nardini, Franco Maria, Orlando, Salvatore, Perego, Raffaele, Trani, Salvatore
Publikováno v:
44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Association for Computing Machinery, 2021, 2217-2221
Modern search engine ranking pipelines are commonly based on large machine-learned ensembles of regression trees. We propose LEAR, a novel - learned - technique aimed to reduce the average number of trees traversed by documents to accumulate the scor
Externí odkaz:
http://arxiv.org/abs/2105.02568
Autor:
Lucchese, Claudio, Nardini, Franco Maria, Orlando, Salvatore, Perego, Raffaele, Trani, Salvatore
Search engine ranking pipelines are commonly based on large ensembles of machine-learned decision trees. The tight constraints on query response time recently motivated researchers to investigate algorithms to make faster the traversal of the additiv
Externí odkaz:
http://arxiv.org/abs/2004.14641
Autor:
Molina, Romina, Loor, Fernando, Gil-Costa, Veronica, Nardini, Franco Maria, Perego, Raffaele, Trani, Salvatore
Publikováno v:
In Journal of Parallel and Distributed Computing September 2021 155:38-49
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Trani, Salvatore1 salvatore.trani@isti.cnr.it, Lucchese, Claudio1, Perego, Raffaele1, Losada, David E.2, Ceccarelli, Diego3, Orlando, Salvatore4
Publikováno v:
Computational Intelligence. Feb2018, Vol. 34 Issue 1, p2-29. 28p.
Autor:
Mele, Ida, Nardini, Franco Maria, Perego, Raffaele, Tonellotto, Nicola, Lira, Vinicius Monteiro De, Muntean, Cristina, Trani, Salvatore
The deliverable D7.1, “Scalability and Robustness Experimental Methodology” consists in a report describing the methodology for assessing the performance of a big data system. In particular, the purpose of the task 7.1 is to develop and to implem
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::46258cc0635a72b27a762f182b77a8c9
Autor:
Nardini, Franco Maria, Lira, Vinicius Monteiro De, Trani, Salvatore, Perego, Raffaele, Muntean, Cristina
This accompanying document for deliverable D4.3 (Models and Tools for Predictive Analytics over Extremely Large Datasets) describes the first version of the mechanisms and tools supporting efficient and effective predictive data analytics over the Bi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::16b6a258616669cd65e25185e6d76a2a