检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Chen, Samuel Yen-Chi Liu, Chen-Yu Chen, Kuan-Cheng Huang, Wei-Jia Chang, Yen-Jui Huang, Wei-Hao Wells Fargo New YorkNY United States Graduate Institute of Applied Physics National Taiwan University Taipei Taiwan Department of Electrical and Electronic Engineering Imperial College London London United Kingdom Imperial College London London United Kingdom Research Institute Taipei Taiwan Quantum Information Center Chung Yuan Christian University Taoyuan City Taiwan Master Program in Intelligent Computing and Big Data Chung Yuan Christian University Taoyuan City Taiwan Jij inc. Tokyo Japan

The rapid advancements in quantum computing (QC) and machine learning (ML) have led to the emergence of quantum machine learning (QML), which integrates the strengths of both fields. Among QML approaches, variational quantum circuits (VQCs), also known as quantum neural networks (QNNs), have shown promise both empirically and theoretically. However, their broader adoption is hindered by reliance on quantum hardware during inference. Hardware imperfections and limited access to quantum devices pose practical challenges. To address this, the Quantum-Train (QT) framework leverages the exponential scaling of quantum amplitudes to generate classical neural network parameters, enabling inference without quantum hardware and achieving significant parameter compression. Yet, designing effective quantum circuit architectures for such quantum-enhanced neural programmers remains non-trivial and often requires expertise in quantum information science. In this paper, we propose an automated solution using differentiable optimization. Our method jointly optimizes both conventional circuit parameters and architectural parameters in an end-to-end manner via automatic differentiation. We evaluate the proposed framework on classification, time-series prediction, and reinforcement learning tasks. Simulation results show that our method matches or outperforms manually designed QNN architectures. This work offers a scalable and automated pathway for designing QNNs that can generate classical neural network parameters across diverse applications. Copyright © 2025, 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

DynaComm: Accelerating distributed CNN training between edges and clouds through dynamic communication scheduling

arXiv

引用

arXiv 2021年

作者： Cai, Shangming Wang, Dongsheng Wang, Haixia Lyu, Yongqiang Xu, Guangquan Zheng, Xi Vasilakos, Athanasios V. Department of Computer Science and Technology Tsinghua University Beijing100084 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen518066 China Big Data School Qingdao Huanghai University Qingdao266427 China College of Intelligence and Computing Tianjin University Tianjin300350 China Department of Computing Macquarie University SydneyNSW2109 Australia College of Mathematics and Computer Science Fuzhou University Fuzhou350116 China School of Electrical and Data Engineering University of Technology Sydney Australia Department of Computer Science Electrical and Space Engineering Lulea University of Technology Lulea97187 Sweden

To reduce uploading bandwidth and address privacy concerns, deep learning at the network edge has been an emerging topic. Typically, edge devices collaboratively train a shared model using real-time generated data through the Parameter Server framework. Although all the edge devices can share the computing workloads, the distributed training processes over edge networks are still time-consuming due to the parameters and gradients transmission procedures between parameter servers and edge devices. Focusing on accelerating distributed Convolutional Neural Networks (CNNs) training at the network edge, we present DynaComm, a novel scheduler that dynamically decomposes each transmission procedure into several segments to achieve optimal layer-wise communications and computations overlapping during run-time. Through experiments, we verify that DynaComm manages to achieve optimal layer-wise scheduling for all cases compared to competing strategies while the model accuracy remains untouched. Copyright © 2021, The Authors. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Active and passive hybrid detection method of power CPS false data injection attacks based on improved AKF and GRU-CNN

arXiv

引用

arXiv 2022年

作者： Qu, Zhaoyang Bo, Xiaoyong Yu, Tong Liu, Yaowei Dong, Yunchang Kan, Zhongfeng Wang, Lei Li, Yang School of Electrical Engineering Northeast Electric Power University Jilin132012 China Electrical and Information Engineering College Jilin Agricultural Science and Technology University Jilin132101 China Jilin Province Engineering Technology Research Center of Power Big Data Intelligent Processing Jilin132012 China Guangxi Power Grid Co. Ltd. Electric Power Research Institute Nanning530013 China State Grid Jilin Electric Power Co. Ltd. Changchun130012 China State Grid Jilin Electric Power Co. Ltd. Jilin Power Supply Company Jilin132011 China

With the deep penetration of the new generation of information technology in the power system, the power system has gradually evolved into a highly coupled cyber-physical systems (CPS), and false data injection attacks (FDIAs) is the most threatening attack among many power CPS network attacks. Aiming at the problem that the existing knowledge-driven detection process of FDIAs has been in a passive detection state for a long time and ignores the advantages of data-driven active capture of features, an active and passive hybrid detection method for power CPS FDIAs with improved adaptive Kalman filter (AKF) and convolutional neural networks (CNN) is proposed in this paper. First, it analyzes the shortcomings of the traditional AKF algorithm in terms of filtering divergence and calculation speed. The state estimation algorithm based on non-negative positive definite adaptive Kalman filter (NDAKF) is improved, and FDIAs passive detection method with similarity Euclidean distance detection and residual detection as the core is constructed. Then, combined with the advantages of gate recurrent unit (GRU) and CNN in terms of temporal memory and feature expression ability, an active detection method of FDIAs based on GRU-CNN hybrid neural network is designed. Finally, the results of joint knowledge-driven and data-driven parallel detection define a mixed fixed calculation formula, and the active and passive hybrid detection method of FDIAs is established considering the characteristic constraints of the parallel mode. The simulation system example of power CPS FDIAs verifies the effectiveness and accuracy of the method proposed in this paper. Copyright © 2022, The Authors. All rights reserved.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

Properties of the diffuse gas component in filaments detected in the Dianoga cosmological simulations

arXiv

引用

arXiv 2024年

作者： Ilc, Samo Fabjan, Dunja Rasia, Elena Borgani, Stefano Dolag, Klaus Faculty of Mathematics and Physics University of Ljubljana Jadranska cesta 19 Ljubljana1000 Slovenia INAF – Osservatorio Astronomico di Trieste via G. B. Tiepolo 11 TriesteI-34143 Italy IFPU Institute for Fundamental Physics of the Universe Via Beirut 2 TriesteI-34014 Italy Department of Physics Astronomy Section University of Trieste via G. B. Tiepolo 11 TriesteI-34131 Italy INFN Instituto Nazionale di Fisica Nucleare Via Valerio 2 TriesteI-34127 Italy ICSC - Italian Research Center on High Performance Computing Big Data and Quantum Computing via Magnanelli 2 Casalecchio di Reno40033 Italy Universitäts-Sternwarte Fakultät für Physik Ludwig-Maximilians-Universität München Scheinerstr.1 München81679 Germany Max-Planck-Institut für Astrophysik Karl-Schwarzschild-Straße 1 Garching85741 Germany

Context. Cosmic filaments are observationally hard to detect. Hydrodynamical cosmological simulations are ideal laboratories where the evolution of the cosmic web can be studied. This allows for easier insight into the nature of the filaments. Aims. We investigate how the intrinsic properties of filaments are evolving in areas extracted from a larger cosmological simulation. We aim to identify significant trends in the properties of Warm-Hot Intergalactic Medium (WHIM) and suggest possible explanations. Methods. To study the filaments and their contents, we select a subset of regions from the Dianoga simulation. We analysed these regions that were simulated with different baryon physics, namely with and without the AGN feedback. We construct the cosmic web using the Sub-space Constrained Mean Shift (SCMS) algorithm and the Sequential Chain Algorithm for Resolving Filaments (SCARF). We examined the basic physical properties of filaments (length, shape, mass, radius) and analysed different gas phases (hot, WHIM and colder gas components) within those structures. The evolution of the global filament properties and the properties of the gas phases were studied in the redshift range 0 1.7. The radial density profile is widening with redshift, meaning that the radius of the filaments is getting larger over time. The fraction of gas mass in the WHIM phase does not depend on the model and is rising towards lower redshifts. However, the included baryon physics has a strong impact on the metallicity of gas in filaments, indicating that the AGN feedback impacts the metal content already at redshifts of z ∼ 2. © 2024, CC BY.

关键词： Cosmology

来源：评论

学校读者我要写书评

暂无评论

Learning Device-invariant And Location-invariant Embedding For Speaker Verification Using Adversarial Multi-task Training

Learning Device-invariant And Location-invariant Embedding F...

引用

Internet of Things and intelligent Applications (ITIA), International Conference on

作者： You-cai Qin Qi-rong Mao Zhong-chen Ma Jing-jing Chen School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China School of Computer Science and Communication Engineering Jiangsu University Jiangsu Engineering Research Center of big data ubiquitous perception and intelligent agriculture applications Zhenjiang China

ISBN: (数字)9781728193014

ISBN: (纸本)9781728193021

Deep speaker embedding model has achieved the satisfactory performance in close-talking speaker verification. However, in the real home environment, the device used to record voice may be different and the distance between speaker and device is constantly changing. These will make performance degradation. In this paper, a novel approach of adversarial multitask training is proposed to solve the problem of device mismatch and location variation by learning device-invariant and location-invariant embeddings. A gradient reversal layer and a device-and-location classifier are added to the speaker validation model in order to build an auxiliary adversarial task. Experiments are conducted on the far-field text-dependent speaker verification database called HI-MIA, the proposed approach achieves 3.38% Equal Error Rate (EER) in close-talking enrollment task and achieves 3.36% EER in far-field enrollment task.

关键词： Task analysis Training databases Feature extraction Microphone arrays Performance evaluation data models

来源：评论

学校读者我要写书评

暂无评论

Comparing Recommendation Algorithms in Session-based E-commerce Sites

Comparing Recommendation Algorithms in Session-based E-comme...

引用

International Conference on intelligent computing, Automation and Systems (ICICAS)

作者： Mingtian Peng Jiahe Zhang Shilin Wen Chi Harold Liu TravelSky Technology Limited Beijing Engineering Research Center of Civil Aviation Big Data and Key Laboratory of Intelligent Passenger Service of Civil Aviation-CAAC Beijing China College of Computer Science Beijing Institute of Technology Beijing China

Recommender systems have become widely used in various website applications. With the integration of deep learning and recommender systems, the classic Session-based Recommender System (SRS) appears, which can obtain implicit feedback from explicit interactions. Some scholars have pro-posed many effective recommendation algorithms to provide better recommendation service in SRS. In order to compare the performance of these session-based recommendation algorithms, we consider a simple E-commerce SRS scenario and choose four representative session-based recommendation algorithms in this paper. Then we do some evaluation experiments. The experimental results show that the combination of local preferences and global preferences will improve the recommendation performance significantly, and for GNNs and RNN s in session recommendation based on deep learning, we also conclude that the prediction effect of GNN s is slightly superior to RNN s on long sessions.

关键词： Deep learning Automation Prediction algorithms Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Practical Interference Exploitation Precoding without Symbol-by-Symbol Optimization: A Block-Level Approach

arXiv

引用

arXiv 2022年

作者： Li, Ang Shen, Chao Liao, Xuewen Masouros, Christos Lee Swindlehurst, A. The School of Information and Communications Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China The State Key Laboratory of Integrated Services Networks Xidian University Shaanxi Xi'An China The Shenzhen Research Institute of Big Data Shenzhen518172 China The Department of Electronic and Electrical Engineering University College London Torrington Place LondonWC1E 7JE United Kingdom The Center for Pervasive Communications and Computing Henry Samueli School of Engineering University of California IrvineCA92697 United States

In this paper, we propose a constructive interference (CI)-based block-level precoding (CI-BLP) approach for the downlink of a multi-user multiple-input single-output (MU-MISO) communication system. Contrary to existing CI precoding approaches which have to be designed on a symbol-by-symbol level, here a constant precoding matrix is applied to a block of symbol slots within a channel coherence interval, thus significantly reducing the computational costs over traditional CI-based symbol-level precoding (CI-SLP) as the CI-BLP optimization problem only needs to be solved once per block. For both PSK and QAM modulation, we formulate an optimization problem to maximize the minimum CI effect over the block subject to a block- rather than symbol-level power budget. We mathematically derive the optimal precoding matrix for CI-BLP as a function of the Lagrange multipliers in closed form. By formulating the dual problem, the original CI-BLP optimization problem is further shown to be equivalent to a quadratic programming (QP) optimization. Numerical results validate our derivations, and show that the proposed CI-BLP scheme achieves improved performance over the traditional CI-SLP method, thanks to the relaxed power constraint over the considered block of symbol slots. Copyright © 2022, The Authors. All rights reserved.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Monaural Speech Separation Joint With Speaker Recognition: A Modeling Approach Based On The Fusion Of Local And Global Information

Monaural Speech Separation Joint With Speaker Recognition: A...

引用

Internet of Things and intelligent Applications (ITIA), International Conference on

作者： Shuang-qing Qian Jing-jing Chen He-ping Song Qi-rong Mao School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China School of Computer Science and Communication Engineering Jiangsu University Jiangsu Engineering Research Center of big data ubiquitous perception and intelligent agriculture applications Zhenjiang China

ISBN: (数字)9781728193014

ISBN: (纸本)9781728193021

In recent years, the dominant speech separation methods model the sequence gradually to encompass global information with the time steps accumulated. However, due to the limited memory capacity of the model, the sequence information in the later position occupies a large proportion, making it impossible to form good interactions between sequences that are farther away. In this paper, we propose a modeling approach Dual-Path Recurrent Neural Network with Transformer (DPRNN-Transformer), which is based on the fusion of local and global information. Through this method, the interrelationships between sequences can be directly established. And the proposed model can effectively merge local and global information in the high-dimensional space by combining both sequence masking and non-masking, thus solving problems such as sequence information forgetting in speech separation area. In addition, in order for the model to extract as much speaker-related feature information as possible, we add the auxiliary task of speaker recognition after speech separation. By co-training with speaker recognition, the speech separation module will be constrained by the additional Triplet loss, thus incorporating speaker information to facilitate separation. Experimental results on WSJ0-2mix dataset show that our proposed method greatly improves the performance of speech separation.

关键词： Decoding Speech recognition Speaker recognition Speech processing Feature extraction Task analysis Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Generating Photospheric Vector Magnetograms of Solar Active Regions for SOHO/MDI Using SDO/HMI and BBSO data

arXiv

引用

arXiv 2022年

作者： Jiang, Haodi Li, Qin Hu, Zhihang Liu, Nian Abduallah, Yasser Jing, Ju Zhang, Genwei Xu, Yan Hsu, Wynne Wang, Jason T.L. Wang, Haimin Institute for Space Weather Sciences New Jersey Institute of Technology University Heights NewarkNJ07102 United States Department of Computer Science New Jersey Institute of Technology University Heights NewarkNJ07102 United States Department of Computer Science Sam Houston State University HuntsvilleTX77341 United States Center for Solar-Terrestrial Research New Jersey Institute of Technology University Heights NewarkNJ07102 United States Big Bear Solar Observatory New Jersey Institute of Technology 40386 North Shore Lane Big Bear CityCA92314 United States Institute of Data Science National University of Singapore 119077 Singapore Department of Computer Science School of Computing National University of Singapore 119077 Singapore

Solar activity is usually caused by the evolution of solar magnetic fields. Magnetic field parameters derived from photospheric vector magnetograms of solar active regions have been used to analyze and forecast eruptive events such as solar flares and coronal mass ejections. Unfortunately, the most recent solar cycle 24 was relatively weak with few large flares, though it is the only solar cycle in which consistent time-sequence vector magnetograms have been available through the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory (SDO) since its launch in 2010. In this paper, we look into another major instrument, namely the Michelson Doppler Imager (MDI) on board the Solar and Heliospheric Observatory (SOHO) from 1996 to 2010. The data archive of SOHO/MDI covers more active solar cycle 23 with many large flares. However, SOHO/MDI data only has line-of-sight (LOS) magnetograms. We propose a new deep learning method, named MagNet, to learn from combined LOS magnetograms, Bx and By taken by SDO/HMI along with Hα observations collected by the big Bear Solar Observatory (BBSO), and to generate vector components Bx′ and By0 , which would form vector magnetograms with observed LOS data. In this way, we can expand the availability of vector magnetograms to the period from 1996 to present. Experimental results demonstrate the good performance of the proposed method. To our knowledge, this is the first time that deep learning has been used to generate photospheric vector magnetograms of solar active regions for SOHO/MDI using SDO/HMI and Hα data. Copyright © 2022, The Authors. All rights reserved.

关键词： Observatories

来源：评论

学校读者我要写书评

暂无评论

An integrated GIS-based multivariate adaptive regression splines-cat swarm optimization for improving the accuracy of wildfire susceptibility mapping

引用

Geocarto International 2023年第1期38卷

作者： Hai, Tao Theruvil Sayed, Biju Majdi, Ali Zhou, Jincheng Sagban, Rafid Band, Shahab S. Mosavi, Amir School of Computer and Information Qiannan Normal University for Nationalities Guizhou Duyun China Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Guizhou Duyun China Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Universiti Teknologi MARA Selangor Shah Alam Malaysia Department of Computer Science Dhofar University Salalah Oman Department of Building and Construction Technologies Engineering Al-Mustaqbal University College Hilla Iraq Department of Computer Technology Engineering Technical Engineering College Al-Ayen University Thi-Qar Iraq Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou Taiwan John von Neumann Faculty of Informatics Obuda University Budapest Hungary German Research Center for Artificial Intelligence Oldenburg Germany Institute of the Information Society University of Public Service Budapest Hungary

A hybrid machine learning method is proposed for wildfire susceptibility mapping. For modeling a geographical information system (GIS) database including 11 influencing factors and 262 fire locations from 2013 to 2018 is used for developing an integrated multivariate adaptive regression splines (MARS). The cat swarm optimization (CSO) algorithm tunes the parameters of the MARS in order to generate accurate susceptibility maps. From the Pearson correlation results, it is observed that land use, temperature, and slope angle have strong correlation with the fire severity. The results demonstrate that the prediction capability of the MARS-CSO model outperforms model tree, reduced error pruning tree and MARS. The resulting wildfire risk map using MARS-CSO reveals that 20% of the study areas is categorized in the very low wildfire risk class, whereas 40% is under the very high class of fire hazard. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： artificial intelligence cat swarm optimization geospatial machine learning natural hazard Wildfire susceptibility

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：