Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Edoardo Manino"'
Autor:
Fatimah K. Aljaafari, Rafael Menezes, Edoardo Manino, Fedor Shmarov, Mustafa A. Mustafa, Lucas C. Cordeiro
Publikováno v:
IEEE Access, Vol 10, Pp 121365-121384 (2022)
Finding software vulnerabilities in concurrent programs is a challenging task due to the size of the state-space exploration, as the number of interleavings grows exponentially with the number of program threads and statements. We propose and evaluat
Externí odkaz:
https://doaj.org/article/095b5024826341b7bc57f51ded5de7e1
Publikováno v:
Tools and Algorithms for the Construction and Analysis of Systems ISBN: 9783031308192
Combining different verification and testing techniques together could, at least in theory, achieve better results than each individual one on its own. The challenge in doing so is how to take advantage of the strengths of each technique while compen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1a8a984316f55b4e4f42812281a9703f
https://doi.org/10.1007/978-3-031-30820-8_33
https://doi.org/10.1007/978-3-031-30820-8_33
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031212215
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f91a3216efbe29eb7ed595eff4912abb
https://doi.org/10.1007/978-3-031-21222-2_3
https://doi.org/10.1007/978-3-031-21222-2_3
Autor:
Xidan Song, Edoardo Manino, Luiz Sena, Erickson Alves, Iury Bessa, Eddie de Lima Filho, Mikel Luján, Lucas Cordeiro
This paper presents QNNVerifier, a tool for verifying implementations of neural networks that takes into accounts the finite word-length(i.e. quantization) of their operations. QNNVerifier achieves this goal by translating the implementation of neura
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3bd44fd1bfe39a37c97df74293d6ec70
Autor:
Luiz Sena, Xidan Song, Erickson Alves, Iury Bessa, Edoardo Manino, Lucas Cordeiro, Eddie de Lima Filho
Artificial Neural Networks (ANNs) are being deployed for an increasing number of safety-critical applications, including autonomous cars and medical diagnosis. However, concerns about their reliability have been raised due to their black-box nature a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1cd2770fa905c6ef711d12ce90f39dbf
http://arxiv.org/abs/2106.05997
http://arxiv.org/abs/2106.05997
Publikováno v:
Complex Networks XI ISBN: 9783030409425
In this paper, we study influence maximization in the voter model in the presence of biased voters (partial zealots) on complex networks. Under what conditions should an external controller with finite budget who aims at maximizing its influence over
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92eccf4869ee5993cd337d400c20faeb
https://doi.org/10.1007/978-3-030-40943-2_10
https://doi.org/10.1007/978-3-030-40943-2_10
Many classification problems are solved by aggregating the output of a group of distinct predictors. In this respect, a popular choice is to assume independence and employ a Naïve Bayes classifier. When we have not just one but multiple classificati
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d4fe5b0caa0d51ae919de4c0fbf2e319
http://wrap.warwick.ac.uk/139664/1/WRAP-On-effiency-data-collection-multiple-Tran-Thanh-2019.pdf
http://wrap.warwick.ac.uk/139664/1/WRAP-On-effiency-data-collection-multiple-Tran-Thanh-2019.pdf
Publikováno v:
Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18)
Scopus-Elsevier
Web of Science
IJCAI
Scopus-Elsevier
Web of Science
IJCAI
The quality of crowdsourced data is often highly variable. For this reason, it is common to collect redundant data and use statistical methods to aggregate it. Empirical studies show that the policies we use to collect such data have a strong impact
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22dfeb57619b1880f847f397f915e9fa
http://hdl.handle.net/10044/1/64569
http://hdl.handle.net/10044/1/64569
Autor:
Xidan Song, Edoardo Manino, Luiz Sena, Erickson Alves, Eddie de Lima Filho, Iury Bessa, Mikel Lujan, Lucas Cordeiro
Publikováno v:
Web of Science
QNNVerifier is the first open-source tool for verifying implementations of neural networks that takes into account the finite word-length (i.e. quantization) of their operands. The novel support for quantization is achieved by employing state-of-the-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::553bf126ee69929ff5a0aa52fe6691d5
https://publons.com/wos-op/publon/55233376/
https://publons.com/wos-op/publon/55233376/
Autor:
Yi Dong, Edoardo Manino, Danilo Carvalho, Julia Rozanova, Xidan Song, Mustafa, Mustafa A., Andre Freitas, Gavin Brown, Mikel Lujan, Xiaowei Huang, Lucas Cordeiro
Publikováno v:
Yi Dong
CEUR Workshop Proceedings
CEUR Workshop Proceedings
The EnnCore project addresses the fundamental security problem of guaranteeing safety, transparency, and robustness in neural-based architectures. Specifically, EnnCore aims at enabling system designers to specify essential conceptual/behavioral prop
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::a9ad5387f2cf7dcff75784e3296a0488
https://livrepository.liverpool.ac.uk/3150295/1/SafeAI_2022_paper_9.pdf
https://livrepository.liverpool.ac.uk/3150295/1/SafeAI_2022_paper_9.pdf