检索结果-内蒙古大学图书馆

Frontiers in Optics + Laser science 2023, FiO, LS 203: Part of Frontiers in Optics + Laser science 2023

作者： Zhu, Chen Huang, Jie Research Center for Optical Fiber Sensing Zhejiang Laboratory Hangzhou311100 China Department of Electrical and Computer Engineering Missouri University of Science and Technology RollaMO65409 United States

A simple yet new sensing method for measurements of refractive index based on microwave-photonic hybrid optical fiber interferometers (optically coherent and incoherent) is proposed and experimentally demonstrated. &#... 详细信息

ISBN: (纸本)9781957171296

关键词： Fabry Perot interferometers Fiber optic couplers Index measurements Long period fiber gratings Optical fibers Tilted fiber Bragg gratings

来源：评论

学校读者我要写书评

暂无评论

Mixture of Gradient: A Unified Enhancing Approach for Deep Learning-Based Wireless Network Optimization

引用

IEEE Internet of Things Journal 2025年第13期12卷 25487-25499页

作者： Cheng, Nan Ma, Longfei Dai, Yanpeng Wang, Xiucheng Li, Qihao Quan, Wei Liang, Hui Dongguan University of Technology School of Electrical Engineering and Intelligentization Dongguan523808 China Xidian University State Key Laboratory of ISN and School of Telecommunications Engineering Xi’an710071 China Dalian Maritime University School of Information Science and Technology Dalian116026 China Jilin University College of Communication Engineering Jilin Changchun130021 China Beijing Jiaotong University School of Electronic and Information Engineering Beijing100044 China Peng Cheng Laboratory Shenzhen518000 China University of Waterloo Department of Electrical and Computer Engineering WaterlooN2L 3G1 Canada

Deep learning plays increasingly important role in future wireless network management and optimization. Existing training methods such as label-based supervised learning and label-free learning have inherent limitations. The performance of supervised learning is limited by labels, while label-free training methods require extensive exploration. To address these limitations, this paper proposes a novel mixture of gradients (MoG) method, which integrates gradients from different sources within the training process in order to improve the convergence performance of neural networks (NNs). Particularly, MoG is a modular, plug-and-play solution requiring no structural modifications to existing NNs. Its implementation necessitates only minor modifications to the loss function, where the label-based supervised loss is combined with a label-free loss through weighted summation. The label-free loss can be either unsupervised loss or reinforcement learning loss. This flexibility allows seamless integration into nearly all NN-based methods, making it applicable to a wide range of wireless optimization problems with minimal implementation cost. Extensive simulations across multiple classic wireless scenarios demonstrate that MoG can significantly enhance the performance of NN decision-making, leading to higher transmission rates. © 2014 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

MKOR: momentum-enabled kronecker-factor-based optimizer using rank-1 updates 23

MKOR: momentum-enabled kronecker-factor-based optimizer usin...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Mohammad Mozaffari Sikan Li Zhao Zhang Maryam Mehri Dehnavi Department of Computer Science University of Toronto Texas Advanced Computing Server Department of Electrical and Computer Engineering Rutgers University

This work proposes a Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates, called MKOR, that improves the training time and convergence properties of deep neural networks (DNNs). Second-order techniques, while enjoying higher convergence rates vs first-order counterparts, have cubic complexity with respect to either the model size and/or the training batch size. Therefore, they exhibit poor scalability and performance in transformer models, e.g. large language models (LLMs), because the batch sizes in these models scale by the attention mechanism sequence length, leading to large model size and batch sizes. MKOR's complexity is quadratic with respect to the model size, alleviating the computation bottlenecks in second-order methods. Because of their high computation complexity, state-of-the-art implementations of second-order methods can only afford to update the second order information infrequently, and thus do not fully exploit the promise of better convergence from these updates. By reducing the communication complexity of the second-order updates, as well as achieving a linear communication complexity, MKOR increases the frequency of second-order updates. We also propose a hybrid version of MKOR (called MKOR-H) that mid-training falls backs to a first order optimizer if the second order updates no longer accelerate convergence. Our experiments show that MKOR outperforms state-of-the-art first-order methods, e.g. the LAMB optimizer, and best implementations of second-order methods, i.e. KAISA/KFAC, up to 2.57× and 1.85 × respectively on BERT-Large-Uncased on 64 GPUs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Elongation of skyrmions by Dzyaloshinskii-Moriya interaction in helimagnetic films

引用

Rare Metals 2022年第9期41卷 3150-3159页

作者： Ying-Ying Dai Han Wang Teng Yang Adekunle O.Adeyeye Zhi-Dong Zhang Shenyang National Laboratory for Materials Science Institute of Metal ResearchChinese Academy of SciencesShenyang110016China Department of Electrical and Computer Engineering National University of SingaporeSingapore117583Singapore Department of Physics Durham UniversityDurhamDH13LEUK

Distortion of skyrmions arouses much attention recently due to the exotic topologic al and dynamic *** the formation mechanism and dynamical behavior of the deformed skyrmions promotes practical spintronic ***,as a typical form of deformation,has been discovered both in experiments and in ***,the intrinsic mechanism is ***,the coexistence of zero-field circular and elongated skyrmions in helimagnetic films is *** elongated skyrmions,which are determined by the intrinsic Dzyaloshinskii-Moriya interaction(DMI),carry the same topological charge as the circular ones and show the skyrmion Hall *** dynamics reveal again the significant role of the intrinsic DMI playing in the skyrmion elongation.

关键词： Elongated skyrmions Dzyaloshinskii-Moriya interaction Skyrmion Hall effect Zero-field skyrmions

来源：评论

学校读者我要写书评

暂无评论

Optimal Parameter Estimation of CAPN Model for Li-ion Battery

Optimal Parameter Estimation of CAPN Model for Li-ion Batter...

引用

2023 International Conference on computer, Electronics and electrical engineering and their Applications, IC2E3 2023

作者： Bharti, Soumya Saini, Vikash Kumar Kumar Yadav, Anshul Kumar, Rajesh Al-Sumaiti, Ameena S. Malaviya National Institute of Technology Department of Electrical Engineering Jaipur India Malaviya National Institute of Technology Center for Energy and Environment Jaipur India Swami Keshvanand Institute of Technology Department of Electrical Engineering Jaipur India Khalifa University Advanced Power and Energy Center Electrical Engineering and Computer Science United Arab Emirates

ISBN: (纸本)9798350338003

Recent developments in battery technology and the reduction of battery costs have resulted in battery energy storage systems (BESS) becoming more economically viable for various power sectors and automobile applications. The degradation of BESS when used in conjunction with photovoltaics (PV) and electric vehicles (EVs) brings new challenges in both technical and economic analysis. Consequently, to ensure the reliability and safety of an energy storage system, modeling battery degradation is critical in order to maintain and replace batteries before potential issues arise. This paper presents a hybrid optimal parameter estimation technique for a combination-factor-based semi-empirical approach to evaluate the state of health (SOH) of Li-ion batteries. The parameters of the proposed model are determined using the SCA optimization algorithm, and the numerical results are confirmed by placing them side-by-side with other heuristic algorithms such as GWO, DE, HHO, and GA. The proposed model outperformed the traditional model with a SOH value of 0.9591 as compared to the previous SOH obtained 0.9467 by the traditional model. © 2023 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Advswap: Covert Adversarial Perturbation with High Frequency Info-Swapping for Autonomous Driving Perception 27

Advswap: Covert Adversarial Perturbation with High Frequency...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Huang, Yuanhao Zhang, Qinfan Xing, Jiandong Cheng, Mengyue Yu, Haiyang Ren, Yilong Xiong, Xiao School of Transportation Science and Engineering Beihang University Beijing100191 China State Key Lab of Intelligent Transportation System Beijing100191 China Zhongguancun Laboratory Beijing100094 China University of Alberta Department of Electrical and Computer Engineering Edmonton Canada

ISBN: (纸本)9798331505929

Perception module of Autonomous vehicles (AVs) are increasingly susceptible to be attacked, which exploit vulnerabilities in neural networks through adversarial inputs, thereby compromising the AI safety. Some researches focus on creating covert adversarial samples, but existing global noise techniques are detectable and difficult to deceive the human visual system. This paper introduces a novel adversarial attack method, AdvSwap, which creatively utilizes wavelet-based highfrequency information swapping to generate covert adversarial samples and fool the camera. AdvSwap employs invertible neural network for selective high-frequency information swapping, preserving both forward propagation and data integrity. The scheme effectively removes the original label data and incorporates the guidance image data, producing concealed and robust adversarial samples. Experimental evaluations and comparisons on the GTSRB and nuScenes datasets demonstrate that AdvSwap can make concealed attacks on common traffic targets. The generates adversarial samples are also difficult to perceive by humans and algorithms. Meanwhile, the method has strong attacking robustness and attacking transferability. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ANIMC: A Soft Approach for Autoweighted Noisy and Incomplete Multiview Clustering

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 192-206页

作者： Fang, Xiang Hu, Yuchong Zhou, Pan Wu, Dapeng Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering The School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Information Storage System Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States

Multiview clustering has wide real-world applications because it can process data from multiple sources. However, these data often contain missing instances and noises, which are ignored by most multiview clustering methods. Missing instances may make these methods difficult to use directly, and noises will lead to unreliable clustering results. In this article, we propose a novel autoweighted noisy and incomplete multiview clustering (ANIMC) approach via a soft autoweighted strategy and a doubly soft regular regression model. First, by designing adaptive semiregularized nonnegative matrix factorization, the soft autoweighted strategy assigns a proper weight to each view and adds a soft boundary to balance the influence of noises and incompleteness. Second, by proposing θ-norm, the doubly soft regularized regression model adjusts the sparsity of our model by choosing different θ. Compared with previous methods, ANIMC has three unique advantages: 1) it is a soft algorithm to adjust our approach in different scenarios, thereby improving its generalization ability;2) it automatically learns a proper weight for each view, thereby reducing the influence of noises;3) it performs doubly soft regularized regression that aligns the same instances in different views, thereby decreasing the impact of missing instances. Extensive experimental results show its superior advantages over other state-of-the-art works. © 2020 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

DGPDHGCN: A Heterogeneous Graph Convolutional Network Method for Predicting Drug-Disease Associations

DGPDHGCN: A Heterogeneous Graph Convolutional Network Method...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhu, Haoran Yu, Tong Ge, Ling Wang, Jianjia Xi'an Jiaotong-Liverpool University School of Ai and Advanced Computing Xjtlu Entrepreneur College Suzhou China Shanghai University School of Computer Engineering and Science China Huaibei People's Hospital Department of Clinical Laboratory Huaibei China

ISBN: (纸本)9798350386226

Drug repositioning is a crucial aspect of biomedical research, and predicting drug-disease associations (DDAs) is a critical step in this process. With the development of deep learning and neural network technologies, Graph Convolutional Networks (GCNs) have achieved significant performances in this research field. Although existing DDAs models have made substantial progress, there is still need for improvement in sufficiently utilizing and integrating information from multiple biological entities. In this study, we propose a Drug-Gene-Protein-Disease Heterogeneous Graph Convolutional Network (DGPDHGCN) model for drug-disease association prediction. First, we construct a heterogeneous network from multiple data sources and establish meta-paths based on the topological information of biological entities. Then, the DGPDHGCN model learns representations of drugs and diseases from similarity and association data of those entities. Finally, we define a score function to quantify the associations between drugs and diseases. Through extensive experiments, we demonstrate that DGPDHGCN outperforms baseline models in DDAs prediction tasks in terms of metrics such as AUPR, F1-score, precision, and recall. The source code and experimental datasets can be found in https://***/Saxon0918/DGPDHGCN © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Incentives in Private Collaborative Machine Learning

arXiv

引用

arXiv 2024年

作者： Sim, Rachael Hwee Ling Zhang, Yehong Hoang, Trong Nghia Xu, Xinyi Low, Bryan Kian Hsiang Jaillet, Patrick Department of Computer Science National University of Singapore Singapore Peng Cheng Laboratory China School of Electrical Engineering and Computer Science Washington State University United States Dept. of Electrical Engineering and Computer Science MIT United States

Collaborative machine learning involves training models on data from multiple parties but must incentivize their participation. Existing data valuation methods fairly value and reward each party based on shared data or model parameters but neglect the privacy risks involved. To address this, we introduce differential privacy (DP) as an incentive. Each party can select its required DP guarantee and perturb its sufficient statistic (SS) accordingly. The mediator values the perturbed SS by the Bayesian surprise it elicits about the model parameters. As our valuation function enforces a privacy-valuation trade-off, parties are deterred from selecting excessive DP guarantees that reduce the utility of the grand coalition’s model. Finally, the mediator rewards each party with different posterior samples of the model parameters. Such rewards still satisfy existing incentives like fairness but additionally preserve DP and a high similarity to the grand coalition’s posterior. We empirically demonstrate the effectiveness and practicality of our approach on synthetic and real-world datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Principled out-of-distribution detection via multiple testing

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 18118-18152页

作者： Akshayaa Magesh Venugopal V. Veeravalli Anirban Roy Susmit Jha Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Champaign IL Computer Science Laboratory SRI International Menlo Park CA

We study the problem of out-of-distribution (OOD) detection, that is, detecting whether a machine learning (ML) model's output can be trusted at inference time. While a number of tests for OOD detection have been proposed in prior work, a formal framework for studying this problem is lacking. We propose a definition for the notion of OOD that includes both the input distribution and the ML model, which provides insights for the construction of powerful tests for OOD detection. We also propose a multiple hypothesis testing inspired procedure to systematically combine any number of different statistics from the ML model using conformal p-values. We further provide strong guarantees on the probability of incorrectly classifying an in-distribution sample as OOD. In our experiments, we find that threshold-based tests proposed in prior work perform well in specific settings, but not uniformly well across different OOD instances. In contrast, our proposed method that combines multiple statistics performs uniformly well across different datasets and neural networks architectures.

关键词： OOD characterization conformal p-values conditional false alarm guarantees Benjamini-Hochberg procedure

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：