检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wang, Shaocong Gao, Yizhao Li, Yi Zhang, Woyu Yu, Yifei Wang, Bo Lin, Ning Chen, Hegan Zhang, Yue Jiang, Yang Wang, Dingchen Chen, Jia Dai, Peng Jiang, Hao Lin, Peng Zhang, Xumeng Qi, Xiaojuan Xu, Xiaoxin So, Hayden Wang, Zhongrui Shang, Dashan Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Key Laboratory of Microelectronic Devices & Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China ACCESS - AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong University of Chinese Academy of Sciences Beijing100049 China Frontier Institute of Chip and System Fudan University Shanghai200433 China College of Computer Science and Technology Zhejiang University Zhejiang310027 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Visual sensors, including 3D LiDAR, neuromorphic DVS sensors, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. Realizing intensive multi-sensory data analysis directly on edge intelligent machines is crucial for numerous emerging edge applications, such as augmented and virtual reality and unmanned aerial vehicles, which necessitates unified data representation, unprecedented hardware energy efficiency and rapid model training. However, multi-sensory data are intrinsically heterogeneous, causing significant complexity in the system development for edge-side intelligent machines. In addition, the performance of conventional digital hardware is limited by the physically separated processing and memory units, known as the von Neumann bottleneck, and the physical limit of transistor scaling, which contributes to the slowdown of Moore's law. These limitations are further intensified by the tedious training of models with ever-increasing sizes. In this study, we propose a novel hardware-software co-design, random resistive memory-based deep extreme point learning machine (DEPLM), that offers efficient unified point set analysis. Data-wise, the multi-sensory data are unified as point sets and can be processed universally. Software-wise, most weights of deep extreme point learning machines are exempted from training, which significantly reduce training complexity. Hardware-wise, nanoscale resistive memory not only enables collocation of memory and processing, mitigating the von Neumann bottleneck and the slowdown of Moore's law, but also leverages the inherent programming stochasticity for generating the random and sparse weights of the DEPLM, which also lessens the impact of read noise. We demonstrate the system's versatility across various data modalities and two different learning tasks. Compared to a conventional digital hardware-based system, our co-design system achieves 5.90×, 21.04×, and 15.79× energy efficiency improv

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Automation Through Machine Learning: Reinvigorating Cyber Security

Automation Through Machine Learning: Reinvigorating Cyber Se...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Jayashree V. Bagade Sukhvinder Singh Dari Rekha Dhivrani Santosh Chowhan G. Ravivarman V Janakiraman Department of Information Technology Vishwakarma Institute of Technology Pune india Symbiosis Law School Nagpur Symbiosis International Pune India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Data Analytics and Mathematical Sciences Jain (Deemed to be University) Bangalore Karnataka India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Department of Mechanical Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Cyber security is predicated heavily on manual efforts to fight malicious assaults, but such processes are increasingly turning into overwhelmed by means of the quantity of threats - a hassle worsened in the course of the global COVID-19 pandemic. This has highlighted the importance of leveraging device studying (ML) to automate cyber protection methods. In this article, we speak how ML may be used to optimize the detection, prevention, and remediations of malicious assaults in an extensive kind of applications and offerings. We discover the various procedures being evolved that may assist make the identity of threats greater accurate and greater effortlessly to be had. We additionally recollect the capacity challenges associated with the software of ML strategies, along with the potential for unfair bias in opposition to positive instructions of customers, and become aware of methods for addressing those issues. Our end emphasizes the significance of leveraging ML in order to enable automation in cyber safety, as well as to make sure the detection of state-of-the-art new threats.

关键词： Automation Pandemics Prevention and mitigation Manuals Machine learning Turning Software Security Protection computer crime

来源：评论

学校读者我要写书评

暂无评论

Octupole topological insulating phase in Brillouin three-dimensional real projective space

arXiv

引用

arXiv 2024年

作者： Qiu, Sichang Hu, Jinbing Yang, Yi Shang, Ce Liu, Shuo Jun Cui, Tie State Key Laboratory of Millimeter Waves Southeast University Nanjing210096 China College of Optical-Electrical Information and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Department of Physics HK Institute of Quantum Science and Technology The University of Hong Kong Pokfulam Hong Kong Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China

Recent advancements in quantum polarization theory have propelled the exploration of topological insulators (TIs) into the realm of higher-order systems, leading to the study of the celebrated two-dimensional (2D) quadrupole and three-dimensional (3D) octupole TIs. Traditionally, these topological phases have been associated with the toroidal topology of the conventional Brillouin zone (BZ). This Letter reports on the discovery of a novel octupole topological insulating phase emerging within the framework of the Brillouin 3D real projective space (3). We theoretically propose the model and its corresponding topological invariant, experimentally construct this insulator within a topological circuit framework, and capture the octupole insulating phase as a localized impedance peak at the circuit's corner. Furthermore, our 3circuit stands out as a pioneering 3D model to simultaneously exhibit both intrinsic, termination-independent symmetry-protected topological phases (SPTPs) and extrinsic, termination-dependent boundary-obstructed topological phases (BOTPs), which broadly encompass 2D surface-obstructed topological phases (SOTPs) and 1D hinge-obstructed topological phases (HOTPs). Our results broaden the topological landscape and provide insights into the band theory within the manifold of the Brillouin 3 © 2024, CC BY.

关键词： Topological insulators

来源：评论

学校读者我要写书评

暂无评论

Dynamic Spectrum Access in Cognitive Radio Networks: A Game-Theoretic Approach

Dynamic Spectrum Access in Cognitive Radio Networks: A Game-...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Dharmesh Dhabliya M. Vigenesh Deepak Minhas M Shalini Sidhant Das S RenukaJyothi Department of Information Technology Vishwakarma Institute of Information Technology Pune Maharashtra India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore India Centre for Interdisciplinary Research for Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai India Chitkara Centre for Research and Development Chitkara University Himachal Pradesh India Department of Biotechnology and Genetics School of Sciences JAIN (Deemed to be University) Bangalore Karnataka India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Cognitive radio networks (CRNs) are a promising technology which could offer better spectrum efficiency and utilization via permitting dynamic spectrum get right of entry to (DSA). Game idea has been an increasing number of hired as a tool for analyzing and addressing optimization problems in CRNs. This abstract discusses the utility of sport theory to the evaluation and optimization of DSA in CRNs. the main consciousness is to broaden a widespread recreation-theoretic approach for DSA that can model numerous styles of interactions among cognitive customers. Specifically, we speak 8 exceptional styles of games that may be used to model the DSA problem, including static, dynamic, and multi-attribute games. Moreover, we speak 3 critical DSA optimization issues: spectrum allocation, spectrum sharing, and energy manipulate. Sooner or later, we speak a few crucial challenges and possibilities for similarly research in this place. Using game principle for DSA in CRNs can assist to enhance the performance of CRNs in terms of throughput, fairness, energy efficiency, and security.

关键词： Games Interference Throughput Energy efficiency Cognitive radio Security Resource management Optimization Standards Sports

来源：评论

学校读者我要写书评

暂无评论

Multi-view Granular-ball Contrastive Clustering 39

Multi-view Granular-ball Contrastive Clustering

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Su, Peng Huang, Shudong Ma, Weihong Xiong, Deng Lv, Jiancheng College of Computer Science Sichuan University Chengdu610065 China Engineering Research Center of Machine Learning and Industry Intelligence Ministry of Education China Information Technology Research Center Beijing Academy of Agriculture and Forestry Sciences Beijing100097 China Stevens Institute of Technology 1 Castle Point Terrace HobokenNJ07030 United States

ISBN: (纸本)157735897X

Previous multi-view contrastive learning methods typically operate at two scales: instance-level and cluster-level. Instance-level approaches construct positive and negative pairs based on sample correspondences, aiming to bring positive pairs closer and push negative pairs further apart in the latent space. Cluster-level methods focus on calculating cluster assignments for samples under each view and maximize view consensus by reducing distribution discrepancies, e.g., minimizing KL divergence or maximizing mutual information. However, these two types of methods either introduce false negatives, leading to reduced model discriminability, or overlook local structures and cannot measure relationships between clusters across views explicitly. To this end, we propose a method named Multi-view Granular-ball Contrastive Clustering (MGBCC). MGBCC segments the sample set into coarse-grained granular balls, and establishes associations between intra-view and cross-view granular balls. These associations are reinforced in a shared latent space, thereby achieving multi-granularity contrastive learning. Granular balls lie between instances and clusters, naturally preserving the local topological structure of the sample set. We conduct extensive experiments to validate the effectiveness of the proposed method. Copyright © 2025, Association for the Advancement of Artificia Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Fast Latent Factor Analysis via a Fuzzy PID-Incorporated Stochastic Gradient Descent Algorithm

arXiv

引用

arXiv 2023年

作者： Li, Jinli Yuan, Ye School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

A high-dimensional and incomplete (HDI) matrix can describe the complex interactions among numerous nodes in various big data-related applications. A stochastic gradient descent (SGD)-based latent factor analysis (LFA) model is remarkably effective in extracting valuable information from an HDI matrix. However, such a model commonly encounters the problem of slow convergence because a standard SGD algorithm learns a latent factor relying on the stochastic gradient of current instance error only without considering past update information. To address this critical issue, this paper innovatively proposes a Fuzzy PID-incorporated SGD (FPS) algorithm with two-fold ideas: 1) rebuilding the instance learning error by considering the past update information in an efficient way following the principle of PID, and 2) implementing hyper-parameters and gain parameters adaptation following the fuzzy rules. With it, an FPS-incorporated LFA model is further achieved for fast processing an HDI matrix. Empirical studies on six HDI datasets demonstrate that the proposed FPS-incorporated LFA model significantly outperforms the state-of-the-art LFA models in terms of computational efficiency for predicting the missing data of an HDI matrix with competitive accuracy. Copyright © 2023, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Intelligent Deep Residual Network based Brain Tumor Detection and Classification 1

Intelligent Deep Residual Network based Brain Tumor Detectio...

引用

1st IEEE International Conference on Automation, Computing and Renewable Systems, ICACRS 2022

作者： Kartheeban, K. Kalyani, Kapula Bommavaram, Sai Krishna Rohatgi, Divya Kathiravan, Mathur Nadarajan Saravanan, S. Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Anand Nagar KrishnanKoil Tamilnadu Srivilliputtur India Department of ECE Aditya College of Engineering and Technology Andhra Pradesh Surampalem India Department of Electronics and Communication Engineering National Institute of Technology Telangana Warangal India Department of CSE Amity University Maharashtra India Department of Biotechnology Dr. N.G.P Arts and Science College Kalapatti Road Tamilnadu Coimbatore India Department of Commerce Dr. Ambedkar Government Arts College Vyasarpadi Tamilnadu Chennai India

ISBN: (纸本)9781665460842

Brain tumor has an impact on people in every age group and considerably raise the global mortality rate. A tumor is comprised of tissue from collected abnormal cells. The benign brain tumor is non-destructive and is not cancerous. Several brain MRI scans are widely required for classifier technique of machine learning (ML) for the segmentation of brain tumors. In optimal classification model, the factors that are to be deliberated include computational resources, classification accuracy, and algorithm performance. This study emphasizes the design of Intelligent DeepResidual Network based Brain Tumor Detection and Classification (IDRN-BTCC) approach. The presented IDRN-BTCC method majorly aims to recognize and classify the presence of BT or not in the medical images. To do so, the projected IDRN-BTCC model follows two subprocesses namely feature extraction and classification. Primarily, residual network (ResNet) model is exploited as a feature extractor which helps to generate feature vectors. In addition, multilayer perceptron (MLP) module is exploited to categorize the medical images into distinct classes. The hyperparameter tuning of the ResNet model takes place using chicken swarm optimization (CSO) algorithm. For examining the enhanced performance of the suggested IDRN-BTCC module, an experimental validation process is tested using benchmark data set and the result highlights the enhancements of the IDRN-BTCC approach over recent methodologies. © 2022 IEEE

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

ImageALCAPA: A 3D Computed Tomography Image Dataset for Automatic Segmentation of Anomalous Left Coronary Artery from Pulmonary Artery

ImageALCAPA: A 3D Computed Tomography Image Dataset for Auto...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： An Zeng Chenxi Mi Dan Pan Qing Lu Xiaowei Xu School of Computer Science Guangdong University of Technology Guangzhou China Department of Computer Science Guangdong Polytechnic Normal University Guangzhou China Department of Computer Science and Engineering University of Notre Dame IN US Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Guangzhou China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Anomalous left coronary artery from pulmonary artery (ALCAPA) is a serious cardiac anomaly, and surgical repair is the main treatment for ALCAPA patients in clinical practice. Recently, 3D printing has been widely adopted in the surgical planning of ALCAPA, which can give surgeons an intuitive structure of the heart especially the coronary arteries. However, before 3D printing is conducted, experienced radiologists need to manually segment the coronary arteries on computed tomography angiography (CTA) images, which is time-consuming, tedious and biased. On the other hand, automatic coronary artery segmentation with normal structures has been extensively studied in the community, but cannot be effectively applied to ALCAPA due to the significant variation of coronary artery structure in ALCAPA. In this paper, we propose ImageALCAPA, the first 3D CTA image dataset of ALCAPA. The proposed dataset contains 30 ALCAPA CTA images, which is of decent size compared with existing medical imaging datasets. We further propose a baseline method that performs multi-task 2D- 3D ensemble for automatic segmentation of ALCAPA. It is shown by experiment that our baseline method outperforms popular existing works on coronary artery segmentation. However, as the highest average Dice Similarity Coefficient of coronary arteries is merely 65%, there is still much room for improvement. To facilitate further research on this challenging problem, our dataset and codes are released to the public [1].

关键词： Image segmentation Three-dimensional displays Codes Computed tomography Lung Surgery Three-dimensional printing

来源：评论

学校读者我要写书评

暂无评论

Ten Challenging Problems in Federated Foundation Models

arXiv

引用

arXiv 2025年

作者： Fan, Tao Gu, Hanlin Cao, Xuemei Chan, Chee Seng Chen, Qian Chen, Yiqiang Feng, Yihui Gu, Yang Geng, Jiaxiang Luo, Bing Liu, Shuoling Ong, Win Kent Ren, Chao Shao, Jiaqi Sun, Chuan Tang, Xiaoli Tae, Hong Xi Tong, Yongxin Wei, Shuyue Wu, Fan Xi, Wei Xu, Mingcong Yang, He Yang, Xin Yan, Jiangpeng Yu, Hao Yu, Han Zhang, Teng Zhang, Yifei Zhang, Xiaojin Zheng, Zhenzhe Fan, Lixin Yang, Qiang WeBank Shenzhen China Universiti Malaya Malaysia Institute of Computing Technology Chinese Academy of Sciences China Duke Kunshan University Kunshan China Innovation Reseach Center EFunds China KTH Royal Institute of Technology Sweden Beihang University China Shanghai Jiao Tong University China Xi’an Jiaotong University China Southwestern University of Finance and Economic China Nanyang Technological University Singapore Huazhong University of Science and Technology China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of federated learning. This combination allows the large foundation models and the small local domain models at the remote clients to learn from each other in a teacher-student learning setting. This paper provides a comprehensive summary of the ten challenging problems inherent in FedFMs, encompassing foundational theory, utilization of private data, continual learning, unlearning, Non-IID and graph data, bidirectional knowledge transfer, incentive mechanism design, game mechanism design, model watermarking, and efficiency. The ten challenging problems manifest in five pivotal aspects: "Foundational Theory," which aims to establish a coherent and unifying theoretical framework for FedFMs. "Data," addressing the difficulties in leveraging domain-specific knowledge from private data while maintaining privacy;"Heterogeneity," examining variations in data, model, and computational resources across clients;"Security and Privacy," focusing on defenses against malicious attacks and model theft;and "Efficiency," highlighting the need for improvements in training, communication, and parameter efficiency. For each problem, we offer a clear mathematical definition on the objective function, analyze existing methods, and discuss the key challenges and potential solutions. This in-depth exploration aims to advance the theoretical foundations of FedFMs, guide practical implementations, and inspire future research to overcome these obstacles, thereby enabling the robust, efficient, and privacy-preserving FedFMs in various real-world applications. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Learning Spatial-Frequency Transformer for Visual Object Tracking

arXiv

引用

arXiv 2022年

作者： Tang, Chuanming Wang, Xiao Bai, Yuanchao Wu, Zhe Zhang, Jianlin Huang, Yongmei University of Chinese Academy of Sciences Beijing108408 China Key Laboratory of Optical Engineering Institute of Optics and Electronics Chinese Academy of Sciences Chengdu610209 China School of Computer Science and Technology Anhui University Hefei230601 China School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China Pengcheng Laboratory Shenzhen518038 China

Recently, some researchers have begun to adopt the Transformer to combine or replace the widely used ResNet as their new backbone network. As the Transformer captures the long-range relations between pixels well using the self-attention scheme, which complements the issues caused by the limited receptive field of CNN. Although their trackers work well in regular scenarios, they simply flatten the 2D features into a sequence to better match the Transformer. We believe these operations ignore the spatial prior of the target object, which may lead to sub-optimal results only. In addition, many works demonstrate that self-attention is actually a low-pass filter, which is independent of input features or keys/queries. That is to say, it may suppress the high-frequency component of the input features and preserve or even amplify the low-frequency information. To handle these issues, in this paper, we propose a unified Spatial-Frequency Transformer that models the Gaussian spatial Prior and High-frequency emphasis Attention (GPHA) simultaneously. To be specific, Gaussian spatial prior is generated using dual Multi-Layer Perceptrons (MLPs) and injected into the similarity matrix produced by multiplying Query and Key features in self-attention. The output will be fed into a softmax layer and then decomposed into two components, i.e., the direct and high-frequency signal. The low- and high-pass branches are rescaled and combined to achieve all-pass, therefore, the high-frequency features will be protected well in stacked self-attention layers. We further integrate the Spatial-Frequency Transformer into the Siamese tracking framework and propose a novel tracking algorithm termed SFTransT. The cross-scale fusion based SwinTransformer is adopted as the backbone, and also a multi-head cross-attention module is used to boost the interaction between search and template features. The output will be fed into the tracking head for target localization. Extensive experiments on short-te

关键词： Low pass filters

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：