As electromagnetic absorbers with wide absorption bandwidth are highly pursued in the cutting-edge electronic and telecommunication industries, the traditional dielectric or magnetic bulky absorbers remain concerns of...As electromagnetic absorbers with wide absorption bandwidth are highly pursued in the cutting-edge electronic and telecommunication industries, the traditional dielectric or magnetic bulky absorbers remain concerns of extending the effective absorption bandwidth. In this work, a dual-principle strategy has been proposed to make a better understanding of the impact of utilizing conductive absorption fillers coupled with implementing artificial structures design on the absorption performance. In the comparison based on the microscopic studies, the carbon nanotubes (CNTs)-based absorbers are confined to narrow operating bandwidth and relatively fixed response frequency range, which can not fulfill the ever-growing demands in the application. With subsequent macroscopic structure design based on the CNTs-based dielectric fillers, the artificial patterns show much more broadened absorption bandwidth, covering the majority of C-band, the whole X-band, and Ku-band, due to the tailored electromagnetic parameters and more reflections and scatterings. The results suggest that the combination of developing microscopic powder/bulky absorbers and macroscopic configuration design will fundamentally extend the effective operating bandwidth of microwave.展开更多
By leveraging the data sample diversity,the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process.However,intermediate classifiers of the earl...By leveraging the data sample diversity,the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process.However,intermediate classifiers of the early exits introduce additional computation overhead,which is unfavorable for resource-constrained edge artificial intelligence(AI).In this paper,we propose an early exit prediction mechanism to reduce the on-device computation overhead in a device-edge co-inference system supported by early-exit networks.Specifically,we design a low-complexity module,namely the exit predictor,to guide some distinctly“hard”samples to bypass the computation of the early exits.Besides,considering the varying communication bandwidth,we extend the early exit prediction mechanism for latency-aware edge inference,which adapts the prediction thresholds of the exit predictor and the confidence thresholds of the early-exit network via a few simple regression models.Extensive experiment results demonstrate the effectiveness of the exit predictor in achieving a better tradeoff between accuracy and on-device computation overhead for early-exit networks.Besides,compared with the baseline methods,the proposed method for latency-aware edge inference attains higher inference accuracy under different bandwidth conditions.展开更多
基金Financial supports from the National Natural Science Foundation of China(No.51971111)the Startup Foundation for Introducing Talent of NUIST,and the Jiangsu Provincial Key Laboratory of Bionic Functional Materials were gratefully acknowledged.
文摘As electromagnetic absorbers with wide absorption bandwidth are highly pursued in the cutting-edge electronic and telecommunication industries, the traditional dielectric or magnetic bulky absorbers remain concerns of extending the effective absorption bandwidth. In this work, a dual-principle strategy has been proposed to make a better understanding of the impact of utilizing conductive absorption fillers coupled with implementing artificial structures design on the absorption performance. In the comparison based on the microscopic studies, the carbon nanotubes (CNTs)-based absorbers are confined to narrow operating bandwidth and relatively fixed response frequency range, which can not fulfill the ever-growing demands in the application. With subsequent macroscopic structure design based on the CNTs-based dielectric fillers, the artificial patterns show much more broadened absorption bandwidth, covering the majority of C-band, the whole X-band, and Ku-band, due to the tailored electromagnetic parameters and more reflections and scatterings. The results suggest that the combination of developing microscopic powder/bulky absorbers and macroscopic configuration design will fundamentally extend the effective operating bandwidth of microwave.
基金fund of the Hong Kong Polytechnic University(P0038174)。
文摘By leveraging the data sample diversity,the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process.However,intermediate classifiers of the early exits introduce additional computation overhead,which is unfavorable for resource-constrained edge artificial intelligence(AI).In this paper,we propose an early exit prediction mechanism to reduce the on-device computation overhead in a device-edge co-inference system supported by early-exit networks.Specifically,we design a low-complexity module,namely the exit predictor,to guide some distinctly“hard”samples to bypass the computation of the early exits.Besides,considering the varying communication bandwidth,we extend the early exit prediction mechanism for latency-aware edge inference,which adapts the prediction thresholds of the exit predictor and the confidence thresholds of the early-exit network via a few simple regression models.Extensive experiment results demonstrate the effectiveness of the exit predictor in achieving a better tradeoff between accuracy and on-device computation overhead for early-exit networks.Besides,compared with the baseline methods,the proposed method for latency-aware edge inference attains higher inference accuracy under different bandwidth conditions.
