This article reviews the theory of fairness in AI-frommachine learning to federated learning,where the constraints on precision AI fairness and perspective solutions are also discussed.For a reliable and quantitative ...This article reviews the theory of fairness in AI-frommachine learning to federated learning,where the constraints on precision AI fairness and perspective solutions are also discussed.For a reliable and quantitative evaluation of AI fairness,many associated concepts have been proposed,formulated and classified.However,the inexplicability of machine learning systems makes it almost impossible to include all necessary details in the modelling stage to ensure fairness.The privacy worries induce the data unfairness and hence,the biases in the datasets for evaluating AI fairness are unavoidable.The imbalance between algorithms’utility and humanization has further reinforced suchworries.Even for federated learning systems,these constraints on precision AI fairness still exist.Aperspective solution is to reconcile the federated learning processes and reduce biases and imbalances accordingly.展开更多
We advanced an emerging federated learning technology in city intelligentization for tackling a real challenge-to learn damaged objects in aerial videos.Ameta-learning system was integrated with the fuzzy broad learni...We advanced an emerging federated learning technology in city intelligentization for tackling a real challenge-to learn damaged objects in aerial videos.Ameta-learning system was integrated with the fuzzy broad learning system to further develop the theory of federated learning.Both the mixed picture set of aerial video segmentation and the 3D-reconstructed mixed-reality data were employed in the performance of the broad federated meta-learning system.The study results indicated that the object classification accuracy is up to 90%and the average time cost in damage detection is only 0.277 s.Consequently,the broad federated meta-learning system is efficient and effective in detecting damaged objects in aerial videos.展开更多
基金the National Academy of Sciences India(NASI),Allahabad,India for the support and to the DirectorNational Institute of Advanced Studies(NIAS),Bengaluru,India for providing the infrastructure facilities to carry out this worksupported by the Shanghai High-Level Base-Building Project for Industrial Technology Innovation.
文摘This article reviews the theory of fairness in AI-frommachine learning to federated learning,where the constraints on precision AI fairness and perspective solutions are also discussed.For a reliable and quantitative evaluation of AI fairness,many associated concepts have been proposed,formulated and classified.However,the inexplicability of machine learning systems makes it almost impossible to include all necessary details in the modelling stage to ensure fairness.The privacy worries induce the data unfairness and hence,the biases in the datasets for evaluating AI fairness are unavoidable.The imbalance between algorithms’utility and humanization has further reinforced suchworries.Even for federated learning systems,these constraints on precision AI fairness still exist.Aperspective solution is to reconcile the federated learning processes and reduce biases and imbalances accordingly.
基金This research was funded by the Strategic Priority Research Program of Chinese Academy of Sciences(XDA20060303)the National Natural Science Foundation of China(41571299)the High-Level Base-Building Project for Industrial Technology Innovation(1021GN204005-A06).
文摘We advanced an emerging federated learning technology in city intelligentization for tackling a real challenge-to learn damaged objects in aerial videos.Ameta-learning system was integrated with the fuzzy broad learning system to further develop the theory of federated learning.Both the mixed picture set of aerial video segmentation and the 3D-reconstructed mixed-reality data were employed in the performance of the broad federated meta-learning system.The study results indicated that the object classification accuracy is up to 90%and the average time cost in damage detection is only 0.277 s.Consequently,the broad federated meta-learning system is efficient and effective in detecting damaged objects in aerial videos.
