Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Gupta, Aishwarya"'
Rigorous testing of machine learning models is necessary for trustworthy deployments. We present a novel black-box approach for generating test-suites for robust testing of deep neural networks (DNNs). Most existing methods create test inputs based o
Externí odkaz:
http://arxiv.org/abs/2408.06766
Autor:
Gupta, Aishwarya, Rahimi Ata, Kimiya
This thesis investigates the impact of implementing an artificial intelligence (AI) model inrecruitment processes, focusing on efficiency and candidate quality. Through quantitativeanalysis, stakeholder insights, and the real-world implementation of
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-531407
Finding suitable health insurance coverage can be challenging for individuals and small enterprises in the USA. The Health Insurance Exchange Public Use Files (Exchange PUFs) dataset provided by CMS offers valuable information on health and dental po
Externí odkaz:
http://arxiv.org/abs/2310.09229
I västvärlden finns det ett överflöde av e-handel applikationer där användare kan köpa och sälja olika produkter och tjänster, både nya och använda. En del av världen där dessa applikationer inte är tillgängliga i samma skala som väst
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-478156
Most existing federated learning methods are unable to estimate model/predictive uncertainty since the client models are trained using the standard loss function minimization approach which ignores such uncertainties. In many situations, however, esp
Externí odkaz:
http://arxiv.org/abs/2206.07562
Publikováno v:
In AEUE - International Journal of Electronics and Communications May 2024 178
Humor and Offense are highly subjective due to multiple word senses, cultural knowledge, and pragmatic competence. Hence, accurately detecting humorous and offensive texts has several compelling use cases in Recommendation Systems and Personalized Co
Externí odkaz:
http://arxiv.org/abs/2104.00933
Publikováno v:
In Physical Communication October 2022 54
Publikováno v:
In AEUE - International Journal of Electronics and Communications August 2022 153
Publikováno v:
Arabian Journal for Science & Engineering (Springer Science & Business Media B.V. ); Oct2024, Vol. 49 Issue 10, p13539-13557, 19p