Using dispersed data and training, federated learning (FL) moves AI capabilities to edge devices or does tasks locally. Many consider FL the start of a new era in AI, yet it is still immature. FL has not garnered the ...
详细信息
Estimating optical flow in dense foggy scenes is a challenging task. The basic assumptions for computing flow such as brightness and gradient constancy become invalid. To address the problem, we introduce a semisuperv...
详细信息
Knowing the rate at which particle radiation releases energy in a material,the“stopping power,”is key to designing nuclear reactors,medical treatments,semiconductor and quantum materials,and many other *** the nucle...
详细信息
Knowing the rate at which particle radiation releases energy in a material,the“stopping power,”is key to designing nuclear reactors,medical treatments,semiconductor and quantum materials,and many other *** the nuclear contribution to stopping power,i.e.,elastic scattering between atoms,is well understood in the literature,the route for gathering data on the electronic contribution has for decades remained costly and reliant on many simplifying assumptions,including that materials are *** establish a method that combines time-dependent density functional theory(TDDFT)and machine learning to reduce the time to assess new materials to hours on a supercomputer and provide valuable data on how atomic details influence electronic *** approach uses TDDFT to compute the electronic stopping from first principles in several directions and then machine learning to interpolate to other directions at a cost of 10 million times fewer *** demonstrate the combined approach in a study of proton irradiation in aluminum and employ it to predict how the depth of maximum energy deposition,the“Bragg Peak,”varies depending on the incident angle—a quantity otherwise inaccessible to modelers and far outside the scales of quantum mechanical *** lack of any experimental information requirement makes our method applicable to most materials,and its speed makes it a prime candidate for enabling quantum-to-continuum models of radiation *** prospect of reusing valuable TDDFT data for training the model makes our approach appealing for applications in the age of materials data science.
Coverage hole restoration and connectivity is a typical problem for underwater wireless sensor networks. In underwater applications like underwater oilfield reservoirs, undersea minerals and monitoring etc., where nod...
详细信息
Hyperdimensional Computing (HDC), a promising alternative to address the limitations of edge devices, is not exempt from the security challenges confronted by machine learning algorithms, in particular, adversarial at...
详细信息
Intelligent-PID (i-PID) control proposed by Fliess is a simple control algorithm. The controller is designed based on ultra-local model, and consisted of PID type controller and derivatives of reference signal and con...
详细信息
We study the risk-aware reinforcement learning (RL) problem in the episodic finite-horizon Markov decision process with unknown transition and reward functions. In contrast to the risk-neutral RL problem, we consider ...
详细信息
Aiming at the problem of low precision and large cleaning error in multi-link similar data mining, a multi-link similar data mining cleaning method based on Bayesian algorithm is proposed in this paper. On the basis o...
详细信息
The development of data-driven soft sensors for modeling complex data, particularly in scenarios characterized by strong nonlinearity, high dimensionality, cross-correlation and autocorrelation, remains a significant ...
详细信息
Deep neural networks (DNNs) have emerged as the most effective programming paradigm for computer vision and natural language processing applications. With the rapid development of DNNs, efficient hardware architecture...
详细信息
Deep neural networks (DNNs) have emerged as the most effective programming paradigm for computer vision and natural language processing applications. With the rapid development of DNNs, efficient hardware architectures for deploying DNN-based applications on edge devices have been extensively studied. Emerging nonvolatile memories (NVMs), with their better scalability, nonvolatility, and good read performance, are found to be promising candidates for deploying DNNs. However, despite the promise, emerging NVMs often suffer from reliability issues, such as stuck-at faults, which decrease the chip yield/memory lifetime and severely impact the accuracy of DNNs. A stuck-at cell can be read but not reprogrammed, thus, stuck-at faults in NVMs may or may not result in errors depending on the data to be stored. By reducing the number of errors caused by stuck-at faults, the reliability of a DNN-based system can be enhanced. This article proposes CRAFT, i.e., criticality-aware fault-tolerance enhancement techniques to enhance the reliability of NVM-based DNNs in the presence of stuck-at faults. A data block remapping technique is used to reduce the impact of stuck-at faults on DNNs accuracy. Additionally, by performing bit-level criticality analysis on various DNNs, the critical-bit positions in network parameters that can significantly impact the accuracy are identified. Based on this analysis, we propose an encoding method which effectively swaps the critical bit positions with that of noncritical bits when more errors (due to stuck-at faults) are present in the critical bits. Experiments of CRAFT architecture with various DNN models indicate that the robustness of a DNN against stuck-at faults can be enhanced by up to 105 times on the CIFAR-10 dataset and up to 29 times on ImageNet dataset with only a minimal amount of storage overhead, i.e., 1.17%. Being orthogonal, CRAFT can be integrated with existing fault-tolerance schemes to further enhance the robustness of DNNs aga
暂无评论