检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Khan, Asifullah Rauf, Zunaira Sohail, Anabia Khan, Abdul Rehman Asif, Hifsa Asif, Aqsa Farooq, Umair Pattern Recognition Lab Department of Computer & Information Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Center for Mathematical Sciences Pakistan Institute of Engineering & Applied Sciences Nilore Islamabad45650 Pakistan Department of Electrical Engineering and Computer Science Khalifa University of Science and Technology Abu Dhabi United Arab Emirates Air University E-9 Islamabad44230 Pakistan

Vision transformers have become popular as a possible substitute to convolutional neural networks (CNNs) for a variety of computer vision applications. These transformers, with their ability to focus on global relationships in images, offer large learning capacity. However, they may suffer from limited generalization as they do not tend to model local correlation in images. Recently, in vision transformers hybridization of both the convolution operation and self-attention mechanism has emerged, to exploit both the local and global image representations. These hybrid vision transformers, also referred to as CNN-Transformer architectures, have demonstrated remarkable results in vision applications. Given the rapidly growing number of hybrid vision transformers, it has become necessary to provide a taxonomy and explanation of these hybrid architectures. This survey presents a taxonomy of the recent vision transformer architectures and more specifically that of the hybrid vision transformers. Additionally, the key features of these architectures such as the attention mechanisms, positional embeddings, multi-scale processing, and convolution are also discussed. In contrast to the previous survey papers that are primarily focused on individual vision transformer architectures or CNNs, this survey uniquely emphasizes the emerging trend of hybrid vision transformers. By showcasing the potential of hybrid vision transformers to deliver exceptional performance across a range of computer vision tasks, this survey sheds light on the future directions of this rapidly evolving architecture. Copyright © 2023, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Diffusion Models

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Peng, Zihao Wang, Xijun Chen, Shengbo Rao, Hong Shen, Cong The School of Mathematics and Computer Science Nanchang University Nanchang330000 China The School of Electronics and Information Technology Sun Yat-sen University Guangzhou510006 China The School of Software Nanchang University Nanchang330000 China The Charles L. Brown Department of Electrical and Computer Engineering University of Virginia CharlottesvilleVA22904 United States

Diffusion models are powerful generative models that can produce highly realistic samples for various tasks. Typically, these models are constructed using centralized, independently and identically distributed (IID) training data. However, in practical scenarios, data is often distributed across multiple clients and frequently manifests non-IID characteristics. Federated Learning (FL) can leverage this distributed data to train diffusion models, but the performance of existing FL methods is unsatisfactory in non-IID scenarios. To address this, we propose FEDDDPM—Federated Learning with Denoising Diffusion Probabilistic Models, which leverages the data generative capability of diffusion models to facilitate model training. In particular, the server uses well-trained local diffusion models uploaded by each client before FL training to generate auxiliary data that can approximately represent the global data distribution. Following each round of model aggregation, the server further optimizes the global model using the auxiliary dataset to alleviate the impact of heterogeneous data on model performance. We provide a rigorous convergence analysis of FEDDDPM and propose an enhanced algorithm, FEDDDPM+, to reduce training overheads. FEDDDPM+ detects instances of slow model learning and performs a one-shot correction using the auxiliary dataset. Experimental results validate that our proposed algorithms outperform the state-of-the-art FL algorithms on the MNIST, CIFAR10 and CIFAR100 datasets. © 2025 IEEE. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Bulk-Switching Memristor-based Compute-In-Memory Module for Deep Neural Network Training

arXiv

引用

arXiv 2023年

作者： Wu, Yuting Wang, Qiwen Wang, Ziyu Wang, Xinxin Ayyagari, Buvna Krishnan, Siddarth Chudzik, Michael Lu, Wei D. Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States Applied Materials Inc. Santa ClaraCA95054 United States

The need for deep neural network (DNN) models with higher performance and better functionality leads to the proliferation of very large models. Model training, however, requires intensive computation time and energy. Memristor-based compute-in-memory (CIM) modules can perform vector-matrix multiplication (VMM) in situ and in parallel, and have shown great promises in DNN inference applications. However, CIM-based model training faces challenges due non-linear weight updates, device variations, and low-precision in analog computing circuits. In this work, we experimentally implement a mixed-precision training scheme to mitigate these effects using a bulk-switching memristor CIM module. Low-precision CIM modules are used to accelerate the expensive VMM operations, with high precision weight updates accumulated in digital units. Memristor devices are only changed when the accumulated weight update value exceeds a pre-defined threshold. The proposed scheme is implemented with a system on chip (SoC) of fully integrated analog CIM modules and digital sub-systems, showing fast convergence of LeNet training to 97.73%. The efficacy of training larger models is evaluated using realistic hardware parameters and shows that that analog CIM modules can enable efficient mix-precision DNN training with accuracy comparable to full-precision software trained models. Additionally, models trained on chip are inherently robust to hardware variations, allowing direct mapping to CIM inference chips without additional re-training. © 2023, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Low c-differentially uniform functions via an extension of Dillon's switching method

arXiv

引用

arXiv 2022年

作者： Li, Chunlei Riera, Constanza Stănică, Pantelimon Department of Informatics University of Bergen Bergen5020 Norway Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen5020 Norway Department of Applied Mathematics Naval Postgraduate School MontereyCA93943-5212 United States

In this paper we generalize Dillon's switching method to characterize the exact c-differential uniformity of functions constructed via this method. More precisely, we modify some PcN/APcN and other functions with known c-differential uniformity in a controllable number of coordinates to render more such functions. We present several applications of the method in constructing PcN and APcN functions with respect to all c ≠ 1. As a byproduct, we generalize some result of [Y. Wu, N. Li, X. Zeng, New PcN and APcN functions over finite fields, Designs Codes Crypt. 89 (2021), 2637-2651]. Computational results rendering functions with low differential uniformity, as well as, other good cryptographic properties are sprinkled throughout the paper. Copyright © 2022, The Authors. All rights reserved.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Doubly-resonant metal-free aluminum nitride electro-optic modulator

Doubly-resonant metal-free aluminum nitride electro-optic mo...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Lipkowitz, Steven T. Grutter, Karen E. Murphy, Thomas E. University of Maryland Department of Electrical and Computer Engineering 8223 Paint Branch Drive College ParkMD20742 United States Laboratory for Physical Sciences 8050 Greenmead Drive College ParkMD20740 United States University of Maryland Institute for Research in Electronics and Applied Physics 8279 Paint Branch Drive College ParkMD20742 United States

Here we use the near field of a dielectric resonant antenna to modulate an on-chip aluminum nitride ring resonator. Using this device we demonstrate entirely metal-free electro-optic modulation at 15.1 GHz. © Opt... 详细信息

ISBN: (纸本)9781957171258

关键词： Aluminum nitride

来源：评论

学校读者我要写书评

暂无评论

Implications of Delayed Reopening in Controlling the COVID-19 Surge in Southern and West-Central USA

引用

Health Data Science 2021年第1期2021卷 78-87页

作者： Raj Dandekar Emma Wang George Barbastathis Chris Rackauckas Department of Computational Science and Engineering Massachusetts Institute of TechnologyCambridgeUSA MA 02139 Department of Electrical Engineering and Computer Sciences Massachusetts Institute of TechnologyCambridgeMA 02139USA Department of Mechanical Engineering Massachusetts Institute of TechnologyCambridgeMA 02139USA Singapore-MIT Alliance for Research and Technology(SMART)Centre Singapore 138602 Department of Applied Mathematics Massachusetts Institute of TechnologyCambridgeMA 02139USA

In the wake of the rapid surge in the COVID-19-infected cases seen in Southern and West-Central USA in the period of June-July 2020,there is an urgent need to develop robust,data-driven models to quantify the effect which early reopening had on the infected case count *** particular,it is imperative to address the question:How many infected cases could have been prevented,had the worst affected states not reopened early?To address this question,we have developed a novel COVID-19 model by augmenting the classical SIR epidemiological model with a neural network *** model decomposes the contribution of quarantine strength to the infection time series,allowing us to quantify the role of quarantine control and the associated reopening policies in the US states which showed a major surge in *** show that the upsurge in the infected cases seen in these states is strongly corelated with a drop in the quarantine/lockdown strength diagnosed by our ***,our results demonstrate that in the event of a stricter lockdown without early reopening,the number of active infected cases recorded on 14 July could have been reduced by more than 40%in all states considered,with the actual number of infections reduced being more than 100,000 for the states of Florida and *** we continue our fight against COVID-19,our proposed model can be used as a valuable asset to simulate the effect of several reopening strategies on the infected count evolution,for any region under consideration.

关键词： COV neural Central

来源：评论

学校读者我要写书评

暂无评论

On the Use of Lightwave Power Transfer in Miniaturized Satellite Communication Systems

On the Use of Lightwave Power Transfer in Miniaturized Satel...

引用

International Symposium on Communication Systems, Networks and Digital Signal Processing, CNSDSP

作者： Nikolaos Kyriatzis Dimitrios Gkiaouris Sotiris A. Tegos Panagiotis D. Diamantoulakis Vasilis K. Papanikolaou Robert Schober George K. Karagiannidis Department of Electrical and Computer Engineering Aristotle University of Thessaloniki Thessaloniki Greece Friedrich-Alexander-University Erlangen-Nuremberg Erlangen Germany Cyber Security Systems and Applied AI Research Center Lebanese American University (LAU) Lebanon

ISBN: (数字)9798350348743

ISBN: (纸本)9798350348750

CubeSats have a significant impact on the satellite communications sector due to their ability to provide rapid, cost-effective, and adaptable improvements to existing satellite networks or to individual missions. The main challenge facing CubeSats is their energy sustainability. Towards this end, we are considering lightwave power transfer (LPT) technology from larger satellites in low earth orbit (LEO) as an alternative power source for CubeSats. We propose a strategy that includes a CubeSat satellite which harvests energy and communicates with a ground base station, utilizing the harvested energy. We formulate an optimization problem for the proposed strategy, aiming to maximize the total harvested energy. Simulation results validate the usefulness of our approach when considering practical assumptions about the satellite orbits.

关键词： Satellites Simulation Low earth orbit satellites Digital signal processing Benchmark testing Orbits CubeSat

来源：评论

学校读者我要写书评

暂无评论

Tackling the Qubit Mapping Problem with Permutation-Aware Synthesis

arXiv

引用

arXiv 2023年

作者： Liu, Ji Younis, Ed Weiden, Mathias Hovland, Paul Kubiatowicz, John Iancu, Costin Mathematics and Computer Science Division Argonne National Laboratory United States Computational Research Division Lawrence Berkeley National Laboratory United States Department of Electrical Engineering and Computer Science University of California Berkeley United States

We propose a novel hierarchical qubit mapping and routing algorithm. First, a circuit is decomposed into blocks that span an identical number of qubits. In the second stage permutation-aware synthesis (PAS), each block is optimized and synthesized in isolation. In the third stage a permutation-aware mapping (PAM) algorithm maps the blocks to the target device based on the information from the second stage. Our approach is based on the following insights: (1) partitioning the circuit into blocks is beneficial for qubit mapping and routing;(2) with PAS, any block can implement an arbitrary input → output qubit mapping (e.g., q0 → q1) that reduces the gate count;and (3) with PAM, for two adjacent blocks we can select input-output permutations that optimize each block together with the amount of communication required at the block boundary. Whereas existing mapping algorithms preserve the original circuit structure and only introduce "minimal" communication via inserting SWAP or bridge gates, the PAS+PAM approach can additionally change the circuit structure and take full advantage of hardware-connectivity. Our experiments show that we can produce better-quality circuits than existing mapping algorithms or commercial compilers (Qiskit, TKET, BQSKit) with maximum optimization settings. For a combination of benchmarks we produce circuits shorter by up to 68% (18% on average) fewer gates than Qiskit, up to 36% (9% on average) fewer gates than TKET, and up to 67% (21% on average) fewer gates than BQSKit. Furthermore, the approach scales, and it can be seamlessly integrated into any quantum circuit compiler or optimization infrastructure. Copyright © 2023, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Sensitivity to control signals in triphasic rhythmic neural systems: a comparative mechanistic analysis via infinitesimal local timing response curves

arXiv

引用

arXiv 2022年

作者： Yu, Zhuojun Rubin, Jonathan E. Thomas, Peter J. Department of Mathematics Applied Mathematics and Statistics Case Western Reserve University ClevelandOH44106 United States Department of Mathematics University of Pittsburgh PittsburghPA15260 United States Department of Mathematics Applied Mathematics and Statistics Department of Biology Department of Electrical Control and Systems Engineering Case Western Reserve University ClevelandOH44106 United States

Similar activity patterns may arise from model neural networks with distinct coupling properties and individual unit dynamics. These similar patterns may, however, respond differently to parameter variations and, specifically, to tuning of inputs that represent control signals. In this work, we analyze the responses resulting from modulation of a localized input in each of three classes of model neural networks that have been recognized in the literature for their capacity to produce robust three-phase rhythms: coupled fast-slow oscillators, near-heteroclinic oscillators, and threshold-linear networks. Triphasic rhythms, in which each phase consists of a prolonged activation of a corresponding subgroup of neurons followed by a fast transition to another phase, represent a fundamental activity pattern observed across a range of central pattern generators underlying behaviors critical to survival, including respiration, locomotion, and feeding. To perform our analysis, we extend the recently developed local timing response curve (lTRC), which allows us to characterize the timing effects due to perturbations, and we complement our lTRC approach with model-specific dynamical systems analysis. Interestingly, we observe disparate effects of similar perturbations across distinct model classes. Thus, this work provides an analytical framework for studying control of oscillations in nonlinear dynamical systems, and may help guide model selection in future efforts to study systems exhibiting triphasic rhythmic activity. Copyright © 2022, The Authors. All rights reserved.

关键词： Linear networks

来源：评论

学校读者我要写书评

暂无评论

Characterizations of Second-order Nonlinear Optical Susceptibility for ϵ-phase Gallium Oxide

Characterizations of Second-order Nonlinear Optical Suscepti...

引用

2022 Compound Semiconductor Week, CSW 2022

作者： Zhou, Jingan Zhao, Xuan Xu, Rui Fu, Kai Li, Tao Xu, Mingfei He, Ziyi Robinson, Jacob T. Zhu, Hanyu Zhang, Xiaodong Zhao, Yuji Rice University Department of Electrical and Computer Engineering HoustonTX77005 United States Rice University Smalley-Curl Institute Applied Physics Graduate Program HoustonTX77005 United States Rice University Department of Materials Science and NanoEngineering HoustonTX77005 United States Arizona State University School of Electrical Computer and Energy Engineering TempeAZ85287 United States Suzhou Institute of Nano-tech and Nano-bionics CAS Key Laboratory of Nanodevices and Applications Suzhou215123 China

ISBN: (数字)9781665453400

ISBN: (纸本)9781665453400

In this work, we report the second-order nonlinear optical susceptibility χ(2) for epsilon phase Gallium Oxide (ϵ-Ga2O3) thin film on sapphire. ϵ-Ga2O3 exhibits hexagonal P63mc space group symmetry, which is a non-centrosymmetric structure with non-zero second order susceptibility. By focusing a pulsed laser beam on to a polished ϵ-Ga2O3 thin film, we collected the generated second harmonic photons with an ultra-sensitive femtowatt photodetector, obtaining effective second-order nonlinear optical susceptibility of χ(2) = 4.89×10-3 pm/V at wavelength of 800 nm. Two different measurement systems collecting reflected and transmitted photons were applied separately to make the result more convincing. The wavelength dependence from 790 nm to 900 nm and polarization dependence from TM mode to TE mode were measured as well. These results will be helpful for the design and fabrication of Ga2O3 based integrated photonics platform in the infrared-visible spectral range. © 2022 IEEE.

关键词： Gallium compounds

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：