There are a wide variety of intelligence accelerators with promising performance and energy efficiency,deployed in a broad range of applications such as computer vision and speech ***,programming productivity hinders ...
详细信息
There are a wide variety of intelligence accelerators with promising performance and energy efficiency,deployed in a broad range of applications such as computer vision and speech ***,programming productivity hinders the deployment of deep learning *** low-level library invoked in the high-level deep learning framework which supports the end-to-end execution with a given model,is designed to reduce the programming burden on the intelligence ***,it is inflexible for developers to build a network model for every deep learning application,which probably brings unnecessary repetitive *** this paper,a flexible and efficient programming framework for deep learning accelerators,FlexPDA,is proposed,which provides more optimization opportunities than the low-level library and realizes quick transplantation of applications to intelligence accelerators for fast *** evaluate FlexPDA by using 10 representative operators selected from deep learning algorithms and an end-to-end *** experimental results validate the effectiveness of FlexPDA,which achieves an end-to-end performance improvement of 1.620x over the low-level library.
Traditional culture refers to a culture that has evolved from civilization and can reflect the characteristics and spirit of a nation. However, at present, the traditional cultural ontology only focuses on modeling an...
详细信息
Unmanned Aerial Vehicles (UAVs) have emerged as integral components in logistics systems, where their potential for efficient delivery services is being explored. However, the limited battery capacity of UAVs poses a ...
详细信息
Association in-between features has been demonstrated to improve the representation ability of data. However, the original association data reconstruction method may face two issues: the dimension of reconstructed dat...
详细信息
Association in-between features has been demonstrated to improve the representation ability of data. However, the original association data reconstruction method may face two issues: the dimension of reconstructed data is undoubtedly higher than that of original data, and adopted association measure method does not well balance effectiveness and efficiency. To address above two issues, this paper proposes a novel association-based representation improvement method, named as AssoRep. AssoRep first obtains the association between features via distance correlation method that has some advantages than Pearson’s correlation coefficient. Then an improved matrix is formed via stacking the association value of any two features. Next, an improved feature representation is obtained by aggregating the original feature with the enhancement matrix. Finally, the improved feature representation is mapped to a low-dimensional space via principal component analysis. The effectiveness of AssoRep is validated on 120 datasets and the fruits further prefect our previous work on the association data reconstruction.
Integrated quantum frequency combs(QFCs)based on microring resonators supplies as an essential resource for expanding the Hilbert-space dimensionality for high-dimensional quantum computing and information *** this wo...
详细信息
Integrated quantum frequency combs(QFCs)based on microring resonators supplies as an essential resource for expanding the Hilbert-space dimensionality for high-dimensional quantum computing and information *** this work,we propose and demonstrate a reconfigurable ring resonator with tunable quality factors to efficiently increase the dimensionality of frequency entanglement,simultaneously,ensuring a high on-chip pair generation rate(PGR)and coincidence-to-accidental ratio(CAR).Our method exploits the asymmetric Mach-Zehnder interferometer instead of the traditional straight waveguide as the coupler of resonators which offer a tunable external coupling coefficient to modulate the quality factor to enlarge the QFCs’bandwidth and thus increase the dimensionality of frequency *** measured the QFCs’joint spectral intensity of 28 frequency pairs under various quality factors ranging from 16.6×10^(4) to 3.4×10^(4).Meanwhile,the measured Schmidt number increased from 11.01 to 24.77,denoting a huge expansion of the Hilbert-space dimensionality from 121 to a record number of 613 dimensions,which agrees well with our theoretical *** addition,the PGR and CAR-another two key parameters for high-quality QFCs-were all measured under different quality factors to verify that our method can significantly increase the Schmidt number and CAR while maintaining a high *** fact,bright QFCs with a total PGR of 4.3 MHz under a 0.48 mW pump power and a mean CAR of 1578 were simultaneously obtained at the highest Schmidt *** method is widely applicable to other material-based ring resonators and can act as a general solution for high-dimensional QFCs.
Virtual staining has shown great promise in realizing a rapid and low-cost clinical alternative for pathological examinations, eliminating the need for chemical reagents and laborious staining procedures. However, mos...
详细信息
Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power ***,most wearable health data is distributed across dfferent organiza...
详细信息
Wearable health monitoring is a crucial technical tool that offers early warning for chronic diseases due to its superior portability and low power ***,most wearable health data is distributed across dfferent organizations,such as hospitals,research institutes,and companies,and can only be accessed by the owners of the data in compliance with data privacy *** first challenge addressed in this paper is communicating in a privacy-preserving manner among different *** second technical challenge is handling the dynamic expansion of the federation without model *** address the first challenge,we propose a horizontal federated learning method called Federated Extremely Random Forest(FedERF).Its contribution-based splitting score computing mechanism significantly mitigates the impact of privacy protection constraints on model *** on FedERF,we present a federated incremental learning method called Federated Incremental Extremely Random Forest(FedIERF)to address the second technical *** introduces a hardness-driven weighting mechanism and an importance-based updating scheme to update the existing federated model *** experiments show that FedERF achieves comparable performance with non-federated methods,and FedIERF effectively addresses the dynamic expansion of the *** opens up opportunities for cooperation between different organizations in wearable health monitoring.
Dear Editor,This letter proposes a symmetry-preserving dual-stream graph neural network(SDGNN) for precise representation learning to an undirected weighted graph(UWG). Although existing graph neural networks(GNNs) ar...
详细信息
Dear Editor,This letter proposes a symmetry-preserving dual-stream graph neural network(SDGNN) for precise representation learning to an undirected weighted graph(UWG). Although existing graph neural networks(GNNs) are influential instruments for representation learning to a UWG, they invariably adopt a unique node feature matrix for illustrating the sole node set of a UWG.
The nonlinear filtering problem has enduringly been an active research topic in both academia and industry due to its ever-growing theoretical importance and practical *** main objective of nonlinear filtering is to i...
详细信息
The nonlinear filtering problem has enduringly been an active research topic in both academia and industry due to its ever-growing theoretical importance and practical *** main objective of nonlinear filtering is to infer the states of a nonlinear dynamical system of interest based on the available noisy measurements. In recent years, the advance of network communication technology has not only popularized the networked systems with apparent advantages in terms of installation,cost and maintenance, but also brought about a series of challenges to the design of nonlinear filtering algorithms, among which the communication constraint has been recognized as a dominating concern. In this context, a great number of investigations have been launched towards the networked nonlinear filtering problem with communication constraints, and many samplebased nonlinear filters have been developed to deal with the highly nonlinear and/or non-Gaussian scenarios. The aim of this paper is to provide a timely survey about the recent advances on the sample-based networked nonlinear filtering problem from the perspective of communication constraints. More specifically, we first review three important families of sample-based filtering methods known as the unscented Kalman filter, particle filter,and maximum correntropy filter. Then, the latest developments are surveyed with stress on the topics regarding incomplete/imperfect information, limited resources and cyber ***, several challenges and open problems are highlighted to shed some lights on the possible trends of future research in this realm.
The emerging mobile robot industry has spurred a flurry of interest in solving the simultaneous localization and mapping(SLAM)***,existing SLAM platforms have difficulty in meeting the real-time and low-pow-er require...
详细信息
The emerging mobile robot industry has spurred a flurry of interest in solving the simultaneous localization and mapping(SLAM)***,existing SLAM platforms have difficulty in meeting the real-time and low-pow-er requirements imposed by mobile *** specialized hardware is promising with regard to achieving high per-formance and lowering the power,designing an efficient accelerator for SLAM is severely hindered by a wide variety of SLAM *** on our detailed analysis of representative SLAM algorithms,we observe that SLAM algorithms advance two challenges for designing efficient hardware accelerators:the large number of computational primitives and ir-regular control *** address these two challenges,we propose a hardware accelerator that features composable com-putation units classified as the matrix,vector,scalar,and control *** addition,we design a hierarchical instruction set for coping with a broad range of SLAM algorithms with irregular control *** results show that,com-pared against an Intel x86 processor,on average,our accelerator with the area of 7.41 mm^(2) achieves 10.52x and 112.62x better performance and energy savings,respectively,across different *** against a more energy-efficient ARM Cortex processor,our accelerator still achieves 33.03x and 62.64x better performance and energy savings,respec-tively.
暂无评论