With the vigorous development of artificial intelligence(AI),intelligence applications based on deep neural networks(DNNs)have changed people’s lifestyles and production efficiency.However,the large amount of computa...With the vigorous development of artificial intelligence(AI),intelligence applications based on deep neural networks(DNNs)have changed people’s lifestyles and production efficiency.However,the large amount of computation and data generated from the network edge becomes the major bottleneck,and the traditional cloud-based computing mode has been unable to meet the requirements of realtime processing tasks.To solve the above problems,by embedding AI model training and inference capabilities into the network edge,edge intelligence(EI)becomes a cutting-edge direction in the field of AI.Furthermore,collaborative DNN inference among the cloud,edge,and end devices provides a promising way to boost EI.Nevertheless,at present,EI oriented collaborative DNN inference is still in its early stage,lacking systematic classification and discussion of existing research efforts.Motivated by it,we have comprehensively investigated recent studies on EI-oriented collaborative DNN inference.In this paper,we first review the background and motivation of EI.Then,we classify four typical collaborative DNN inference paradigms for EI,and analyse their characteristics and key technologies.Finally,we summarize the current challenges of collaborative DNN inference,discuss future development trends and provide future research directions.展开更多
For the sparse linear equations K x = b, where K arising from optimization and discretization of some PDEs is symmetric and indefinite, it is shown that the L (L) over bar(T) factorization can be used to provide an &#...For the sparse linear equations K x = b, where K arising from optimization and discretization of some PDEs is symmetric and indefinite, it is shown that the L (L) over bar(T) factorization can be used to provide an 'exact' preconditioner for SYMMLQ and UZAWA algorithms. 'Inexact' preconditioner derived from approximate factorization is used in the numerical experiments.展开更多
基金National Natural Science Foundation of China(Nos.61931011,62072303 and 61872310)the Key-area Research and Development Program of Guangdong Province,China(No.2021B0101400003)+2 种基金Hong Kong Research Grants Council(RGC)Research Impact Fund,China(No.R5060-19)General Research Fund(Nos.152221/19E,152203/20E and 152244/2IE)Shenzhen Science and Technology Innovation Commission,China(No.JCYJ20200109142008673).
文摘With the vigorous development of artificial intelligence(AI),intelligence applications based on deep neural networks(DNNs)have changed people’s lifestyles and production efficiency.However,the large amount of computation and data generated from the network edge becomes the major bottleneck,and the traditional cloud-based computing mode has been unable to meet the requirements of realtime processing tasks.To solve the above problems,by embedding AI model training and inference capabilities into the network edge,edge intelligence(EI)becomes a cutting-edge direction in the field of AI.Furthermore,collaborative DNN inference among the cloud,edge,and end devices provides a promising way to boost EI.Nevertheless,at present,EI oriented collaborative DNN inference is still in its early stage,lacking systematic classification and discussion of existing research efforts.Motivated by it,we have comprehensively investigated recent studies on EI-oriented collaborative DNN inference.In this paper,we first review the background and motivation of EI.Then,we classify four typical collaborative DNN inference paradigms for EI,and analyse their characteristics and key technologies.Finally,we summarize the current challenges of collaborative DNN inference,discuss future development trends and provide future research directions.
文摘For the sparse linear equations K x = b, where K arising from optimization and discretization of some PDEs is symmetric and indefinite, it is shown that the L (L) over bar(T) factorization can be used to provide an 'exact' preconditioner for SYMMLQ and UZAWA algorithms. 'Inexact' preconditioner derived from approximate factorization is used in the numerical experiments.
