检索结果-内蒙古大学图书馆

MBS: A High-Precision Approximation Method for Softmax and Efficient Hardware Implementation

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年

作者： Wu, Yuanchen Xie, Zhiheng Pan, Hongbing Wang, Yuxuan Nanjing Univ Sch Elect Sci & Engn Nanjing 210023 Peoples R China

The softmax function needs to be frequently used in the multi-head attention layer of Transformer networks. Compared to DNNs and other networks, Transformers have higher computational complexity, requiring higher accuracy and hardware performance for softmax function calculations. Therefore, we propose mixed-base softmax (MBS) for the first time for the approximation of the softmax function. This method combines exponential functions with bases of 2 and 4, which is advantageous for hardware implementation. MBS has a high similarity to the softmax function and demonstrates advanced performance during inference in Transformer network. Through algorithm transformation and hardware optimization, we have designed a low-complexity and highly parallel hardware architecture, which only occupies few additional hardware resources compared to base-2 softmax but achieves higher accuracy. Experimental results show that, under TSMC 90nm CMOS technology at the frequency of 0.5 GHz, our design can achieve the efficiency of 236.18 Gps/(mm(2)& sdot;mW) with the area of 4234 mu m(2). Furthermore, MBS exhibits higher computational accuracy and inference precision compared with base-2 softmax.

关键词： Hardware Accuracy Transformers Computational modeling Computer architecture Approximation methods Approximation algorithms Linear approximation inference algorithms Frequency modulation Softmax function mixed-base softmax transformer neural network high-efficiency hardware

来源：评论

学校读者我要写书评

暂无评论

Deep Networks as Denoising algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2025年第4期71卷 2930-2954页

作者： Mei, Song Wu, Yuchen Univ Calif Berkeley Dept Stat Berkeley CA 94720 USA Univ Calif Berkeley Dept Elect Engn & Comp Sci Berkeley CA 94720 USA Univ Penn Wharton Sch Dept Stat & Data Sci Philadelphia PA 19104 USA

We investigate the efficiency of deep neural networks for approximating scoring functions in diffusion-based generative modeling. While existing approximation theories leverage the smoothness of score functions, they suffer from the curse of dimensionality for intrinsically high-dimensional data. This limitation is pronounced in graphical models such as Markov random fields, where the approximation efficiency of score functions remains unestablished. To address this, we note score functions can often be well-approximated in graphical models through variational inference denoising algorithms. Furthermore, these algorithms can be efficiently represented by neural networks. We demonstrate this through examples, including Ising models, conditional Ising models, restricted Boltzmann machines, and sparse encoding models. Combined with off-the-shelf discretization error bounds for diffusion-based sampling, we provide an efficient sample complexity bound for diffusion-based generative modeling when the score function is learned by deep neural networks.

关键词： Approximation algorithms Graphical models Diffusion models inference algorithms Noise reduction Mathematical models Standards Computational modeling Risk minimization Residual neural networks Diffusion model graphical model residual neural network

来源：评论

学校读者我要写书评

暂无评论

A Single-Stage Photovoltaic Module Defect Detection Method Based on Optimized YOLOv8

引用

IEEE ACCESS 2025年 13卷 27805-27817页

作者： Gao, Yihong Pang, Chengxin Zeng, Xinhua Jiang, Pengyi Shanghai Univ Elect Power Shanghai 200000 Peoples R China Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China NYU New York NY 10012 USA

Defect detection in photovoltaic (PV) modules presents significant challenges. In the presence of inconspicuous or small-scale defects, downsampling operations can cause features to vanish, and computational complexity increases as the model deepens, resulting in reduced detection accuracy, higher latency, and challenges in deploying the model on edge devices with limited computational resources. In response, this article proposes a single-stage object detection model based on YOLOv8, the PSA-PVdetector (PSA-det). The core innovation of PSA-det is the novel Partial Spatial Attention (PSA) mechanism, which integrates Partial Convolution (PConv) with Spatial Attention (SA) to optimize feature extraction and reduce computational overhead. For small-scale defect detection, a Multi-Channel Feature Fusion (MCFF) detection head is designed to enable finer-grained center prediction. Additionally, ShapeIoU is employed as the bounding box regression metric, enhancing the classical IoU by incorporating bounding box shape, thereby improving defect localization accuracy. Experimental results demonstrate that PSA-det achieves an mAP50 of 87.2% on the Panel-2 dataset and 72.0% on the Solar dataset. On the Nvidia Jetson Xavier NX DK platform, PSA-det achieves an inference latency as low as 2.6 ms, effectively balancing accuracy and real-time performance.

关键词： Feature extraction Defect detection Head YOLO Convolution Accuracy Inspection Computational modeling inference algorithms Termination of employment YOLOv8 photovoltaic defect detection edge deployment partial convolution spatial attention

来源：评论

学校读者我要写书评

暂无评论

Path Selection via Mutual Coherence Optimization in Network Monitoring

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2025年第2期22卷 1461-1472页

作者： Fan, XiaoBo Xihua Univ Sch Elect Engn & Elect Informat Chengdu 610039 Peoples R China

Periodically monitoring the state of internal links is important for network diagnosis. One of the major problems in tomography-based network monitoring is to select which paths to measure. In this paper, we propose a new path selection scheme by means of optimizing the mutual coherence of the routing matrix. The proposed scheme exploits the sparse characteristic of link status and follows the matrix design methods in sparse signal theory. By picking the paths with the minimum average mutual coherence, we can recover a sparse vector more accurately. The effectiveness of the proposed algorithms is analyzed theoretically. We conduct simulation experiments of delay estimation on both synthetic and real topologies. The results demonstrate that our scheme can select the most useful paths for network tomography with lowest cost in an acceptable time.

关键词： Monitoring Routing Tomography Probes inference algorithms Coherence Costs Vectors Topology Network topology Network monitoring path selection matrix design mutual coherence

来源：评论

学校读者我要写书评

暂无评论

Counterfactual Music Recommendation for Mitigating Popularity Bias

引用

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2025年第2期12卷 851-861页

作者： Yuan, Jidong Gao, Bingyu Wang, Xiaokang Liu, Haiyang Zhang, Lingyin Beijing Jiaotog Univ Key Lab Big Data & Artificial Intelligence Transpo Minist Educ Beijing 100044 Peoples R China Beijing Jiaotog Univ Sch Comp Sci & Technol Beijing 100044 Peoples R China Beijing Univ Posts & Telecommun Sch Econ & Management Beijing 100876 Peoples R China

Music recommendation systems aim to suggest tracks that users may enjoy. However, the accuracy of recommendation results is affected by popularity bias. Previous studies have focused on mitigating the direct effect of single-item popularity in video, news, or e-commerce recommendations, but have overlooked the multisource popularity biases in music recommendations. This article proposes a causal inference-based method to reduce the influence of both track and artist popularity. First, we construct a causal graph that encompasses users, tracks, and artists within the context of music recommendations. Next, we employ matrix factorization in conjunction with counterfactual inference theory to mitigate the popularity effects of artists and tracks, taking into account both the natural direct and indirect effects of these entities on music recommendations. Experimental results evaluated on four music recommendation datasets indicate that our method outperforms other baselines and effectively alleviates the popularity bias of both tracks and artists.

关键词： Recommender systems Music Training inference algorithms Electronic commerce Accuracy Measurement Vectors Transportation Tracking loops Counterfactual inference music recommendation popularity bias

来源：评论

学校读者我要写书评

暂无评论

Intelligence Evaluating Computational Power: A Multi-Factor Method

引用

IEEE ACCESS 2025年 13卷 27398-27415页

作者： Huang, Yuhuan Li, Hang Lu, Dongdong Zhang, Zhe Tie, Wenjie Suzhou Key Lab Microwave Imaging Proc & Applicat T Suzhou 215000 Peoples R China Suzhou Aerosp Informat Res Inst Suzhou 215000 Peoples R China Natl Key Lab Microwave Imaging Beijing 100000 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst Beijing 100000 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100000 Peoples R China

With the rapid development of hardware technologies and the continuous optimization of deep learning tasks, accurately evaluating the computational power of artificial intelligence (AI) systems has become a critical requirement. However, the diversity of hardware architectures and the complexity of deep learning tasks have hindered the establishment of a widely accepted unified evaluation standard. To address this issue, we propose a novel evaluation method that integrates key metrics such as model performance, computational throughput, and energy efficiency, providing a more comprehensive and reliable assessment of AI hardware computational capabilities. Through benchmark tests on servers, statistical analysis of the method, and case studies in cloud, edge, and terminal environments, this approach not only ensures the accuracy of existing evaluation frameworks but also reveals the key characteristics and potential influencing factors of hardware computational power from multiple dimensions.

关键词： Computational modeling Benchmark testing Artificial intelligence Training inference algorithms Deep learning Analytical models Performance evaluation Accuracy Predictive models Deep learning benchmark test AI hardware performance evaluation model performance assessment

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Driven Channel Estimation for Asymmetrical Massive MIMO Systems

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第1期74卷 911-924页

作者： Yang, Ruming Xu, Shu Zhu, Zhiming Li, Chunguo Huang, Yongming Yang, Luxi Southeast Univ Sch Informat Sci & Engn Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China Purple Mt Labs Nanjing 211111 Peoples R China

A novel asymmetrical massive multiple-input multiple-output (MIMO) system has recently emerged as a crucial solution for reducing hardware complexity and alleviating the data processing pressure. However, the absence of channel reciprocity in this system presents unique challenges when directly applying traditional channel estimation methods, inevitably leading to performance loss. Deep learning approaches hold promise for achieving improved channel estimation performance by implicitly learning channel features. Unfortunately, deep learning approaches are often designed empirically. It is critical to utilize prior knowledge to develop an efficient deep neural network (DNN), especially for wireless communication systems. This paper explores a knowledge-driven DNN design approach and introduces a deep learning-based channel estimation framework for asymmetrical transceivers. The channel estimation problem is decoupled into channel denoising and information inference problems. Two novel DNNs are proposed to eliminate noise and exploit correlative features for reconstructing the missing channel information, respectively. Extensive simulations demonstrate that our proposed channel estimation framework can significantly eliminate noise effects, even in low signal-to-noise ratio regimes, and outperform traditional estimators and other deep learning-based methods. Moreover, ablation studies also validate the effectiveness of our knowledge-driven network structure design approach.

关键词： Channel estimation Massive MIMO Receiving antennas Radio frequency Transmitting antennas inference algorithms Noise reduction Asymmetrical transceiver channel estimation channel transfer deep learning uplink-to-downlink

来源：评论

学校读者我要写书评

暂无评论

A Seed Growth Algorithm for Local Clustering in Complex Networks

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2024年第6期11卷 5878-5891页

作者： Tsai, Feng-Sheng Hsu, Sheng-Yi Shih, Mau-Hsiang China Med Univ Dept Biomed Informat Taichung 404328 Taiwan China Med Univ Hosp Res Ctr Interneural Comp Taichung 404327 Taiwan Ever Fortune AI Co Ltd Taichung 406040 Taiwan China Med Univ China Med Univ Hosp Res Ctr Interneural Comp Taichung 404327 Taiwan

A seed growth algorithm based on a local connectivity rule for cluster formation in complex networks is introduced. That accompanies with the cluster normalization algorithm, the parameter determination process, and the pseudocluster inference process, forming the coherent algorithms and formalizing the categories within the realm of the cluster space. The prime clusters can be extracted from the cluster space, so that the overlapping complexity of clusters is confined to the prime clusters. To decide unequivocally whether the coherent algorithms are efficient, we have to simulate on the overlapping stochastic block networks. Our simulation shows that the dice coefficient of the prime cluster corresponding to the overlapping target cluster is 0.978 +/- 0.024 on average. It decodes the underlying meaning that the coherent algorithms can efficiently search out the prime clusters containing almost the same nodes as the overlapping clusters. It provides a firm foundation for a simulation on the Caenorhabditis elegans neuronal network, unraveling the neurons DD04, PDB, VA08, VB06, VB07, VD07, and VD08 lying in the major overlap of clusters, among them the ablation of DD04 and PDB in biological experiments has shown to result in a pronounced loss of controllability of motor behavior.

关键词： Clustering algorithms Neurons Partitioning algorithms inference algorithms Complex networks Linear programming Stochastic processes Caenorhabditis elegans neuronal networks local cluster formation locomotor control cluster overlap stochastic block networks

来源：评论

学校读者我要写书评

暂无评论

Learning From Crowds Using Graph Neural Networks With Attention Mechanism

引用

IEEE TRANSACTIONS ON BIG DATA 2025年第1期11卷 86-98页

作者： Zhang, Jing Wu, Ming Sun, Zeyi Zhou, Cangqi Southeast Univ Sch Cyber Sci & Engn Nanjing 211189 Jiangsu Peoples R China Southeast Univ Engn Res Ctr Blockchain Applicat Supervis & Manage Minist Educ Nanjing 211189 Jiangsu Peoples R China Hohai Univ Sch Artificial Intelligence & Automat Nanjing 211100 Jiangsu Peoples R China Zhejiang Lab Inst Artificial Intelligence Knowledge Engn Res Ctr Hangzhou 311121 Zhejiang Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China

Crowdsourcing has been playing an essential role in machine learning since it can obtain a large number of labels in an economical and fast manner for training increasingly complex learning models. However, the application of crowdsourcing learning still faces several challenges such as the low quality of crowd labels and the urgent requirement for learning models adapting to the label noises. There have been many studies focusing on truth inference algorithms to improve the quality of labels obtained by crowdsourcing. Comparably, end-to-end predictive model learning in crowdsourcing scenarios, especially using cutting-edge deep learning techniques, is still in its infant stage. In this paper, we propose a novel graph convolutional network-based framework, namely CGNNAT, which models the correlation of instances by combining the GCN model with an attention mechanism to learn more representative node embeddings for a better understanding of the bias tendency of crowd workers. Furthermore, a specific projection processing layer is employed in CGNNAT to model the reliability of each crowd worker, which makes the model an end-to-end neural network directly trained by noisy crowd labels. Experimental results on several real-world and synthetic datasets show that the proposed CGNNAT outperforms state-of-the-art and classical methods in terms of label prediction.

关键词： Crowdsourcing Noise measurement Data models Biological system modeling Deep learning Task analysis inference algorithms Learning from crowds repeated labeling graph neural networks attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Efficient Solvers for Wyner Common Information With Application to Multi-Modal Clustering

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 2025年第3期71卷 2054-2074页

作者： Huang, Teng-Hui El Gamal, Hesham Univ Sydney Sch Elect & Comp Engn Camperdown NSW 2050 Australia Univ Sydney Fac Engn Camperdown NSW 2050 Australia

In this work, we propose computationally efficient solvers for novel extensions of Wyner common information. By separating information sources into bipartite, the proposed Bipartite common information framework has difference-of-convex structure for efficient non-convex optimization. In known joint distribution cases, our difference-of-convex algorithm(DCA)-based solver has a provable convergence guarantee to local stationary points. As for unknown distribution settings, the insights from DCA combined with the exponential family of distributions for parameterization allows for closed-form expressions for efficient estimation. Furthermore, we show that the Bipartite common information applies to multi-modal clustering without employing ad-hoc clustering algorithms. Empirically, our solvers outperform state-of-the-art methods in clustering accuracy and running time over a range of non-trivial multi-modal clustering datasets with different number of data modalities.

关键词： Optimization Vectors Indexes Convergence Mutual information Feature extraction Clustering algorithms Unsupervised learning inference algorithms Entropy Wyner common information algorithms optimization variational inference conditional independence multi-modal learning clustering unsupervised

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：