Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Hazem Fahmy"'
Publikováno v:
Water Alternatives, Vol 3, Iss 1, Pp 122-136 (2010)
This paper outlines the development of an approach (and a set of tools) for 'light' integrated water resources management (IWRM): that is, IWRM that is opportunistic, adaptive and incremental in nature and clearly focused on sustainable service deliv
Externí odkaz:
https://doaj.org/article/8f8fa77c7c1443c4bb9ce02d22d6fcac
Publikováno v:
info:eu-repo/grantAgreement/EC/H2020/694277
When Deep Neural Networks (DNNs) are used in safety-critical systems, engineers should determine the safety risks associated with failures (i.e., erroneous outputs) observed during testing. For DNNs processing images, engineers visually inspect all f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::86cf7437551647b7032570ea12f739cf
https://doi.org/10.1145/3569935
https://doi.org/10.1145/3569935
Publikováno v:
info:eu-repo/grantAgreement/EC/H2020/694277
Deep neural networks (DNNs) have demonstrated superior performance over classical machine learning to support many features in safety-critical systems. Although DNNs are now widely used in such systems (e.g., self driving cars), there is limited prog
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e8bc564d97f31488770793e33056dd2
Publikováno v:
info:eu-repo/grantAgreement/EC/H2020/694277
We present HUDD, a tool that supports safety analysis practices for systems enabled by Deep Neural Networks (DNNs) by automatically identifying the root causes for DNN errors and retraining the DNN. HUDD stands for Heatmap-based Unsupervised Debuggin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1906e70ae49adcaf71c0212dc126494
Autor:
Hazem Fahmy
Publikováno v:
Prairie Schooner. 95:72-73
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::517e5e073aaf4976aca2ee1f3a5dac22
https://doi.org/10.1353/psg.2021.0013
https://doi.org/10.1353/psg.2021.0013
Autor:
Hazem Fahmy
Publikováno v:
Social Research: An International Quarterly. 79:349-376
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ad71a46395055c6db6b8b97521700d67
https://doi.org/10.1353/sor.2012.0003
https://doi.org/10.1353/sor.2012.0003
Publikováno v:
IEEE Transactions on Reliability
Deep neural networks (DNNs) are increasingly important in safety-critical systems, for example, in their perception layer to analyze images. Unfortunately, there is a lack of methods to ensure the functional safety of DNN-based components. We observe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::df8ae1d25a733e9f0f6b4a99c106bd76