检索结果-内蒙古大学图书馆

On RNN-Based k-WTA Models With Time-Dependent Inputs

IEEE/CAA Journal of Automatica Sinica 2022年第11期9卷 2034-2036页

作者： Mei Liu Mingsheng Shang the Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714 the Chongqing School University of Chinese Academy of SciencesChongqing 400714China

Dear editor,This letter identifies two weaknesses of state-of-the-art k-winnerstake-all(k-WTA)models based on recurrent neural networks(RNNs)when considering time-dependent inputs,i.e.,the lagging error and the infeas... 详细信息

关键词： letter convergence finite

来源：评论

学校读者我要写书评

暂无评论

SLMP: A Scientific Literature Management Platform Based on Large Language Models 15

SLMP: A Scientific Literature Management Platform Based on L...

引用

15th IEEE International Conference on Knowledge Graph, ICKG 2024

作者： Guo, Menghao Jiang, Jinling Wu, Fan Sun, Shanxin Zhang, Chen Li, Wenhui Sun, Zeyi Chen, Guangyong Wu, Xindong Research Center for Life Sciences Computing Zhejiang Lab Hangzhou China Research Center for Data Hub and Security Zhejiang Lab Hangzhou China Research Center for High Efficiency Computing System Zhejiang Lab Hangzhou China Hefei University of Technology Key Laboratory of Knowledge Engineering With Big Data Hefei China

ISBN: (纸本)9798331508821

This paper presents a Scientific Literature Management Platform (SLMP, demo link1 ) based on large language models (LLMs). The platform consists of four modules: literature management, literature extraction, literature retrieval, and question answering. The core techniques used to support the four modules across the platform include a fine-tuned model PaperExtractGPT and a continual pre-training model ChatPaperGPT based on ChatGLM2 using the data from scientific research literature, responsible for information extraction and communication, respectively. Due to their powerful capabilities in natural language understanding and generation, LLMs can understand complex scientific concepts based on the provided contexts, and thus generate high-quality texts and conduct in-depth information retrieval and question answering. Our platform can help researchers manage and utilize literature more effectively and efficiently for finding relevant literature, obtaining required information, and generating new knowledge. © 2024 IEEE.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Current Control for Asymmetric Six-phase Permanent Magnet Motors with Less Computation and Optimized Voltage Vector Magnitude

Model Predictive Current Control for Asymmetric Six-phase Pe...

引用

2022 International Conference on Smart Energy and Electrical Engineering, SEEE 2022

作者： Sun, Jinyu Chen, Fubing Huai'An Key Laboratory of Big Data Intelligent Computing and Analysis China The School of Computer Science and Technology Huaiyin Normal University Huaian223001 China

For the sake of the fixed magnitude of candidate control sets, the conventional model predictive current control (MPCC) for asymmetric six-phase permanent magnet motors suffers from huge harmonic currents. This article designs a novel MPCC that aims to improve operational performance. First, virtual-voltage vector (VV) sets are synthesized as the new candidate vectors to restrain harmonic currents. Then, a simplified method for evaluating voltage vectors is used to alleviate the computation in the enumeration process. Moreover, the duty cycle modulation with the deadbeat solution is introduced to optimize the magnitude of the VV. The modulation range can be expanded by utilizing null vectors, which will significantly reduce the torque fluctuations and flux ripples. The experiments are conducted to verify the designed control strategy. © Published under licence by IOP Publishing Ltd.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Knowledge circuits in pretrained transformers 24

Knowledge circuits in pretrained transformers

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yunzhi Yao Ningyu Zhang Zekun Xi Mengru Wang Ziwen Xu Shumin Deng Huajun Chen Zhejiang University National University of Singapore NUS-NCS Joint Lab Singapore Zhejiang University and Zhejiang Key Laboratory of Big Data Intelligent Computing

ISBN: (纸本)9798331314385

The remarkable capabilities of modern large language models are rooted in their vast repositories of knowledge encoded within their parameters, enabling them to perceive the world and engage in reasoning. The inner workings of how these models store knowledge have long been a subject of intense interest and investigation among researchers. To date, most studies have concentrated on isolated components within these models, such as the Multilayer Perceptrons and attention head. In this paper, we delve into the computation graph of the language model to uncover the knowledge circuits that are instrumental in articulating specific knowledge. The experiments, conducted with GPT2 and TinyLLAMA, have allowed us to observe how certain information heads, relation heads, and Multilayer Perceptrons collaboratively encode knowledge within the model. Moreover, we evaluate the impact of current knowledge editing techniques on these knowledge circuits, providing deeper insights into the functioning and constraints of these editing methodologies. Finally, we utilize knowledge circuits to analyze and interpret language model behaviors such as hallucinations and in-context learning. We believe the knowledge circuits hold potential for advancing our understanding of Transformers and guiding the improved design of knowledge editing. Code and data are available in https://***/zjunlp/KnowledgeCircuits.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Signal Demodulation in Underwater Wireless Optical Communications

引用

China Communications 2024年第5期21卷 297-313页

作者： Ma Shuai Yang Lei Ding Wanying Li Hang Zhang Zhongdan Xu Jing Li Zongyan Xu Gang Li Shiyin Department of Strategic and Advanced Interdisciplinary Research Peng Cheng LaboratoryShenzhen 518055China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China Data-driven Intelligent Information System Laboratory Shenzhen Research Institute of Big DataShenzhen 518172China Ocean College Zhejiang UniversityZhoushan 316021China State Key Laboratory of Millimeter Waves Southeast UniversityNanjing 210096China

The underwater wireless optical communication(UWOC)system has gradually become essential to underwater wireless communication *** other existing works on UWOC systems,this paper evaluates the proposed machine learningbased signal demodulation methods through the selfbuilt experimental *** on such a platform,we first construct a real signal dataset with ten modulation ***,we propose a deep belief network(DBN)-based demodulator for feature extraction and multi-class feature *** also design an adaptive boosting(Ada Boost)demodulator as an alternative scheme without feature filtering for multiple modulated ***,it is demonstrated by extensive experimental results that the Ada Boost demodulator significantly outperforms the other *** also reveals that the demodulator accuracy decreases as the modulation order increases for a fixed received optical power.A higher-order modulation may achieve a higher effective transmission rate when the signal-to-noise ratio(SNR)is higher.

关键词： AdaBoost DBN machine learning signal demodulation

来源：评论

学校读者我要写书评

暂无评论

Task Separation and Knowledge Sharing for Class Incremental Learning 5

Task Separation and Knowledge Sharing for Class Incremental ...

引用

5th International Conference on intelligent computing and Human-Computer Interaction, ICHCI 2024

作者： Zhang, Jiali Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China School of Mathematics and Information Science Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China

ISBN: (纸本)9798350368284

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Inductive Relation Prediction by Disentangled Subgraph Structure

引用

Tsinghua Science and Technology 2024年第5期29卷 1566-1579页

作者： Guiduo Duan Rui Guo Wenlong Luo Guangchun Luo Tianxi Huang Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of ChinaChengdu 611731Chinaand also with Trusted Cloud Computing and Big Data Key Laboratory of Sichuan ProvinceChengdu 611731China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Hangzhou NetEase Cloud Music Technology Co. Ltd.Hangzhou 310052China Department of Fundamental Courses Chengdu Textile CollegeChengdu 611700China

Currently,most existing inductive relation prediction approaches are based on subgraph structures,with subgraph features extracted using graph neural networks to predict ***,subgraphs may contain disconnected regions,which usually represent different semantic *** not all semantic information about the regions is helpful in relation prediction,we propose a relation prediction model based on a disentangled subgraph structure and implement a feature updating approach based on relevant semantic *** indirectly achieve the disentangled subgraph structure from a semantic perspective,the mapping of entity features into different semantic spaces and the aggregation of related semantics on each semantic space are *** disentangled model can focus on features having higher semantic relevance in the prediction,thus addressing a problem with existing approaches,which ignore the semantic differences in different subgraph ***,using a gated recurrent neural network,this model enhances the features of entities by sorting them by distance and extracting the path information in the ***,it is shown that when there are numerous disconnected regions in the subgraph,our model outperforms existing mainstream models in terms of both Area Under the Curve-Precision-Recall(AUC-PR)and Hits@*** prove that semantic differences in the knowledge graph can be effectively distinguished and verify the effectiveness of this method.

关键词： disentangled subgraph structure knowledge graph completion Gated Recurrent Unit(GRU) feature updating

来源：评论

学校读者我要写书评

暂无评论

An attention-based cascade R-CNN model for sternum fracture detection in X-ray images

引用

CAAI Transactions on Intelligence Technology 2022年第4期7卷 658-670页

作者： Yang Jia Haijuan Wang Weiguang Chen Yagang Wang Bin Yang School of Computer Xi'an University of Posts and TelecommunicationsXi'anShaanxiChina Shaanxi Key Laboratory of Network Data Intelligent Processing Xi'an University of Posts and TelecommunicationsXi'anShaanxiChina Xi'an Key Laboratory of Big Data and Intelligent Computing Xi'anShaanxiChina Department of Radiology Xi'an Honghui HospitalXi'anChina

Fracture is one of the most common and unexpected *** not treated in time,it may cause serious consequences such as joint stiffness,traumatic arthritis,and nerve *** computer vision technology to detect fractures can reduce the workload and misdiagnosis of fractures and also improve the fracture detection ***,there are still some problems in sternum fracture detection,such as the low detection rate of small and occult *** this work,the authors have constructed a dataset with 1227 labelled X-ray images for sternum fracture *** authors designed a fully automatic fracture detection model based on a deep convolution neural network(CNN).The authors used cascade R-CNN,attention mechanism,and atrous convolution to optimise the detection of small fractures in a large X-ray image with big local *** authors compared the detection results of YOLOv5 model,cascade R-CNN and other state-of-the-art *** authors found that the convolution neural network based on cascade and attention mechanism models has a better detection effect and arrives at an mAP of 0.71,which is much better than using the YOLOv5 model(mAP=0.44)and cascade R-CNN(mAP=0.55).

关键词： attention mechanism cascade R-CNN fracture detection X-ray image

来源：评论

学校读者我要写书评

暂无评论

An ε-domination based two-archive 2 algorithm for many-objective optimization

引用

Journal of Systems Engineering and Electronics 2022年第1期33卷 156-169页

作者： WU Tianwei AN Siguang HAN Jianqiang SHENTU Nanying College of Mechanical and Electrical Engineering China Jiliang UniversityHangzhou 310018China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jilang UniversityHangzhou 310018China

The two-archive 2 algorithm(Two_Arch2) is a manyobjective evolutionary algorithm for balancing the convergence,diversity,and complexity using diversity archive(DA) and convergence archive(CA).However,the individuals in DA are selected based on the traditional Pareto dominance which decreases the selection pressure in the high-dimensional *** traditional algorithm even cannot converge due to the weak selection ***,Two_Arch2 adopts DA as the output of the algorithm which is hard to maintain diversity and coverage of the final solutions synchronously and increase the complexity of the *** increase the evolutionary pressure of the algorithm and improve distribution and convergence of the final solutions,an ε-domination based Two_Arch2 algorithm(ε-Two_Arch2) for many-objective problems(MaOPs) is proposed in this *** ε-Two_Arch2,to decrease the computational complexity and speed up the convergence,a novel evolutionary framework with a fast update strategy is proposed;to increase the selection pressure,ε-domination is assigned to update the individuals in DA;to guarantee the uniform distribution of the solution,a boundary protection strategy based on I_(ε+) indicator is designated as two steps selection strategies to update individuals in *** evaluate the performance of the proposed algorithm,a series of benchmark functions with different numbers of objectives is *** results demonstrate that the proposed method is competitive with the state-of-the-art multi-objective evolutionary algorithms and the efficiency of the algorithm is significantly improved compared with Two_Arch2.

关键词： many-objective optimization ε-domination boundary protection strategy two-archive algorithm

来源：评论

学校读者我要写书评

暂无评论

Gradient-Based Differential kWTA Network With Application to Competitive Coordination of Multiple Robots

引用

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1452-1463页

作者： Mei Liu Xiaoyan Zhang Mingsheng Shang Long Jin School of Information Science and Engineering Lanzhou UniversityLanzhou 730000 State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining 810016China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Shenzhen Research Institute Lanzhou UniversityShenzhen 518063China

Aiming at the k-winners-take-all(kWTA)operation,this paper proposes a gradient-based differential kWTA(GDk WTA)*** obtaining the network,theorems and related proofs are provided to guarantee the exponential convergence and noise resistance of the proposed GD-kWTA ***,numerical simulations are conducted to substantiate the preferable performance of the proposed network as compared with the traditional ***,the GD-k WTA network,backed with a consensus filter,is utilized as a robust control scheme for modeling the competition behavior in the multi-robot coordination,thereby further demonstrating its effectiveness and feasibility.

关键词： Consensus filter k-winners-take-all(kWTA) multirobot coordination noise resistance

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：