检索结果-内蒙古大学图书馆

5th International Symposium on Robotics and Intelligent Manufacturing Technology, ISRIMT 2023

作者： Zheng, Yonghang Peng, Yan Qu, Dong Shang Hai University School of Computer Engineering and Science Shanghai200444 China Institute of Artificial Intelligence Shanghai University Shanghai200444 China Shanghai Artificial Intelligence Laboratory 200433 China

ISBN: (纸本)9798350316087

This paper proposes a hybrid auction algorithm that combines neural networks, parallel auction algorithm, and conflict resolution strategy to solve the frontier point task allocation problem in the multi-robot cooperative exploration process under weak communication environment. This paper integrates a trained fully connected neural network into each robot. Each robot takes the frontier point position, its own position, battery remaining power, communication neighbor number and other information as the input of the neural network, and the output of the neural network is the robot's bid for each frontier point. The robots are divided into several groups according to the communication topology structure. Each robot group adopts an improved parallel auction algorithm to perform the frontier point task allocation within the group. However, unlike the traditional parallel auction algorithm, each robot's bid is not obtained by the cost function, but by the neural network. And before sending the task allocation result to the robot that executes the task, several robot groups' auctioneers need to ensure the rationality and consistency of the task allocation through the conflict resolution strategy. After the conflict resolution stage is over, each auctioneer broadcasts the task allocation result within their own group. In the experiment, We compared our method with the Greedy algorithm. Our method has more advantages as the scene gets larger and is more robust than the Greedy algorithm. © 2023 IEEE.

关键词： Industrial robots

来源：评论

学校读者我要写书评

暂无评论

The most tenuous group query

引用

Frontiers of computer science 2023年第2期17卷 197-208页

作者： Na LI Huaijie ZHU Wenhao LU Ningning CUI Wei LIU Jian YIN Jianliang XU Wang-Chien LEE School of Computer Science and Engineering Sun Yat-Sen UniversityGuangzhou 510006China Laboratory of Big Data Analysis and Processing Guangzhou 510006China School of Artificial Intelligence Sun Yat-Sen UniversityGuangzhou 510006China Department of Computer Science Anhui UniversityHefei 230601China Department of Computer Science Hong Kong Baptist UniversityHong Kong 999077China Department of Computer Science The Pennsylvania State UniversityState College 19019USA

Rtecently a lot of works have been investigating to find the tenuous groups,i.e.,groups with few social interactions and weak relationships among members,for reviewer selection and psycho-educational group ***,the metrics(e.g.,k-triangle,k-line,and k-tenuity)used to measure the tenuity,require a suitable k value to be specified which is difficult for users without background ***,in this paper we formulate the most tenuous group(MTG)query in terms of the group distance and average group distance of a group measuring the tenuity to eliminate the influence of parameter k on the tenuity of the *** address the MTG problem,we first propose an exact algorithm,namely MTGVDIS,which takes priority to selecting those vertices whose vertex distance is large,to generate the result group,and also utilizes effective filtering and pruning *** MTGVDIS is not fast enough,we design an efficient exact algorithm,called MTG-VDGE,which exploits the degree metric to sort the vertexes and proposes a new combination order,namely degree and reverse based branch and bound(DRBB).MTG-VDGE gives priority to those vertices with small *** a large p,we further develop an approximation algorithm,namely MTG-VDLT,which discards candidate attendees with high degree to reduce the number of vertices to be *** experimental results on real datasets manifest that the proposed algorithms outperform existing approaches on both efficiency and group tenuity.

关键词： tenuous group pruning strategy social network group query

来源：评论

学校读者我要写书评

暂无评论

Momentum Posterior Regularization for Multi-hop Dense Retrieval 31

Momentum Posterior Regularization for Multi-hop Dense Retrie...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Xia, Zehua Wu, Yuyang Xia, Yiyun Nguyen, Cam-Tu State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science Nanjing University China School of Artificial Intelligence Nanjing University China

ISBN: (纸本)9798891761964

Multi-hop question answering (QA) often requires sequential retrieval (multi-hop retrieval), where each hop retrieves missing knowledge based on information from previous hops. To facilitate more effective retrieval, we aim to distill knowledge from a posterior retrieval, which has access to posterior information like an answer, into a prior retrieval used during inference when such information is unavailable. Unfortunately, current methods for knowledge distillation in one-time retrieval are ineffective for multi-hop QA due to two issues: 1) Posterior information is often defined as the response (i.e. the answer), which may not clearly connect to the query without intermediate retrieval;and 2) The large knowledge gap between prior and posterior retrievals makes existing distillation methods unstable, even resulting in performance loss. As such, we propose MoPo (Momentum Posterior Regularization) with two key innovations: 1) Posterior information of one hop is defined as a query-focus summary from the golden knowledge of the previous and current hops;2) We develop an effective training strategy where the posterior retrieval is updated along with the prior retrieval via momentum moving average method, allowing smoother and effective distillation. Experiments on HotpotQA and StrategyQA demonstrate that MoPo outperforms existing baselines in both retrieval and downstream QA tasks. © 2025 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Say No to the Poisonous Fungi: An Effective Strategy for Reducing 0-1 Cost in FungiCLEF2024 25

Say No to the Poisonous Fungi: An Effective Strategy for Red...

引用

25th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF 2024

作者： Tan, Bao-Feng Li, Yang-Yang Wang, Peng Zhao, Lin Wei, Xiu-Shen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

The FungiCLEF2024 competition endeavors to precisely identify fungi species leveraging both metadata and image analysis. Pivotal to the success of this competition are two crucial evaluation metrics: minimizing the error rate and the 0-1 cost loss resulting from misclassification. To reduce the identification error rate, we introduce a Dynamic MLP framework, drawing inspiration from [1]. This approach effectively integrates image and metadata embeddings through recursive blocks, utilizing matrix multiplication for deep fusion of information. To further address the issue of 0-1 cost, we devise a novel probability-based screening strategy, which initially consolidates poisonous fungi categories into a single class, then employs marginal expected loss and a threshold parameter α to optimize the recall rate for poisonous species. These approaches significantly reduce the error rate and 0-1 cost associated with misclassification and achieve a score of 0.5548 on the private leaderboard, securing the third-place ranking. The code is available at https://***/bftan1949/FungiCLEF2024. © 2024 Copyright for this paper by its authors.

关键词： 0-1 cost loss Fine-grained image recognition Fungi Species Identification Open-Set

来源：评论

学校读者我要写书评

暂无评论

Multibranch Co-training to Mine Venomous Feature Representation: A Solution to SnakeCLEF2024 25

Multibranch Co-training to Mine Venomous Feature Representat...

引用

25th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF 2024

作者： Wang, Peng Li, Yangyang Tan, Bao-Feng Zhou, Yi-Chao Li, Yong Wei, Xiu-Shen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

The SnakeCLEF2024 competition aims to develop an advanced algorithm capable of automatically identifying snake species from images. Accurate identification of snake species in snakebite cases can assist doctors in administering targeted antivenom, which is crucial for effective treatment. In this paper, we propose a multibranch co-training strategy based on Convolutional Neural Networks (CNNs) as the solution. During the training phase, our method consists of three branches which can be trained end-to-end. The first branch is used for the classification of all species and generates a gating coefficient. The second branch specifically focuses on venomous snakes, while the third branch concentrates on harmless species. The gating coefficient determines which of these branches will be utilized. During the inference phase, we only retain the first branch. Our solution significantly enhances the model's ability to distinguish between venomous and harmless snake species and achieve an accuracy of 69.83% and scored 83.57% on the track1 on the private leaderboard, which is the 1st place among all participants. The code is available at https://***/pengdadaaa/SnakeCLEF2024. © 2024 Copyright for this paper by its authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment 38

DFA-GNN: Forward Learning of Graph Neural Networks by Direct...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhao, Gongpei Wang, Tao Lang, Congyan Jin, Yi Li, Yidong Ling, Haibin Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education China School of Computer Science & Technology Beijing Jiaotong University China Department of Computer Science Stony Brook University United States

Graph neural networks (GNNs) are recognized for their strong performance across various applications, with the backpropagation (BP) algorithm playing a central role in the development of most GNN models. However, despite its effectiveness, BP has limitations that challenge its biological plausibility and affect the efficiency, scalability and parallelism of training neural networks for graph-based tasks. While several non-backpropagation (non-BP) training algorithms, such as the direct feedback alignment (DFA), have been successfully applied to fully-connected and convolutional network components for handling Euclidean data, directly adapting these non-BP frameworks to manage non-Euclidean graph data in GNN models presents significant challenges. These challenges primarily arise from the violation of the independent and identically distributed (i.i.d.) assumption in graph data and the difficulty in accessing prediction errors for all samples (nodes) within the graph. To overcome these obstacles, in this paper we propose DFA-GNN, a novel forward learning framework tailored for GNNs with a case study of semi-supervised learning. The proposed method breaks the limitations of BP by using a dedicated forward training mechanism. Specifically, DFA-GNN extends the principles of DFA to adapt to graph data and unique architecture of GNNs, which incorporates the information of graph topology into the feedback links to accommodate the non-Euclidean characteristics of graph data. Additionally, for semi-supervised graph learning tasks, we developed a pseudo error generator that spreads residual errors from training data to create a pseudo error for each unlabeled node. These pseudo errors are then utilized to train GNNs using DFA. Extensive experiments on 10 public benchmarks reveal that our learning framework outperforms not only previous non-BP methods but also the standard BP methods, and it exhibits excellent robustness against various types of noise and attacks. © 2024 Neura

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

High-Speed Railway 2024年第2期2卷 101-109页

作者： Jiaxu Guo Ding Ding Peihan Yang Qi Zou Yaping Huang School of Computer Science and Technology Beijing Jiaotong UniversityBeijing 100044China Key Laboratory of Big Data&Artificial Intelligence in Transportation Ministry of EducationBeijing 100044China

It is of great significance to improve the efficiency of railway production and operation by realizing the fault knowledge association through the efficient data mining ***,high utility quantitative frequent pattern mining algorithms in the field of data mining still suffer from the problems of low time-memory performance and are not easy to scale *** the context of such needs,we propose a related degree-based frequent pattern mining algorithm,named Related High Utility Quantitative Item set Mining(RHUQI-Miner),to enable the effective mining of railway fault *** algorithm constructs the item-related degree structure of fault data and gives a pruning optimization strategy to find frequent patterns with higher related degrees,reducing redundancy and invalid frequent ***,it uses the fixed pattern length strategy to modify the utility information of the item in the mining process so that the algorithm can control the length of the output frequent pattern according to the actual data situation and further improve the performance and practicability of the *** experimental results on the real fault dataset show that RHUQI-Miner can effectively reduce the time and memory consumption in the mining process,thus providing data support for differentiated and precise maintenance strategies.

关键词： High utility Quantitative Frequent pattern mining Related degree pruning Fixed pattern length

来源：评论

学校读者我要写书评

暂无评论

Unsupervised pseudoinverse hashing learning model for rare astronomical object retrieval

引用

science China(Technological sciences) 2022年第6期65卷 1338-1348页

作者： WANG Ke GUO Ping LUO ALi XU MingLiang Artificial Intelligence Research Center School of Computer and Artificial IntelligenceZhengzhou UniversityZhengzhou 450001China School of Systems Science Beijing Normal UniversityBeijing 100875China Key Laboratory of Optical Astronomy National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100012China

Searching for rare astronomical objects based on spectral data is similar to finding needles in a haystack owing to their rarity and the immense data volume gathered from large astronomical spectroscopic *** this paper,we propose a novel automated approximate nearest neighbor search method based on unsupervised hashing learning for rare spectra *** proposed method employs a multilayer neural network using autoencoders as the local compact feature *** are trained with a non-gradient learning algorithm with graph Laplace *** algorithm also simplifies the tuning of network architecture hyperparameters and the learning control ***,the graph Laplace regularization can enhance the robustness by reducing the sensibility to *** proposed model is data-driven;thus,it can be viewed as a general-purpose retrieval *** proposed model is evaluated in experiments and real-world applications where rare Otype stars and their subclass are retrieved from the dataset obtained from the Large Sky Area Multi-Object Fiber Spectroscopic Telescope(Guo Shoujing Telescope).The experimental and application results show that the proposed model outperformed the baseline methods,demonstrating the effectiveness of the proposed method in rare spectra retrieval tasks.

关键词： compact features unsupervised hashing object retrieval pseudoinverse learning

来源：评论

学校读者我要写书评

暂无评论

Competition for roadside camera monocular 3D object detection

引用

National science Review 2023年第6期10卷 34-37页

作者： Jinrang Jia Yifeng Shi Yuli Qu Rui Wang Xing Xu Hai Zhang Baidu Inc. Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University College of Software Jilin University School of Computer Science and Engineering University of Electronic Science and Technology of China Pazhou Laboratory (Huangpu) School of Mathematics Northwest University

INTRODUCTION Accurate environment perception is a critical topic in autonomous driving and intelligent *** environmental perception methods mostly rely on on-board ***,limited by the installation height,thereare problems such as blind spots and unstable long-range perception in vehicle perceptual ***,with the rapid improvement of intelligent infrastructure,it has become possible to use roadside cameras for traffic environment *** from the increased height when compared with on-boardsensors,roadside cameras can obtain a larger perceptual field of view and realize long-range observation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization 27

A First-Order Multi-Gradient Algorithm for Multi-Objective B...

引用

27th European Conference on artificial intelligence, ECAI 2024

作者： Ye, Feiyang Lin, Baijiong Cao, Xiaofeng Zhang, Yu Tsang, Ivor W. Department of Computer Science and Engineering Southern University of Science and Technology China Australian Artificial Intelligence Institute University of Technology Sydney Australia The Hong Kong University of Science and Technology Guangzhou China School of Artificial Intelligence Jilin University China Shanghai Artificial Intelligence Laboratory China Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9781643685489

In this paper, we study the Multi-Objective Bi-Level Optimization (MOBLO) problem, where the upper-level subproblem is a multi-objective optimization problem and the lower-level subproblem is for scalar optimization. Existing gradient-based MOBLO algorithms need to compute the Hessian matrix, causing the computational inefficient problem. To address this, we propose an efficient first-order multi-gradient method for MOBLO, called FORUM. Specifically, we reformulate MOBLO problems as a constrained multi-objective optimization (MOO) problem via the value-function approach. Then we propose a novel multi-gradient aggregation method to solve the challenging constrained MOO problem. Theoretically, we provide the complexity analysis to show the efficiency of the proposed method and a non-asymptotic convergence result. Empirically, extensive experiments demonstrate the effectiveness and efficiency of the proposed FORUM method in different learning problems. In particular, it achieves state-of-the-art performance on three multi-task learning benchmark datasets. © 2024 The Authors.

关键词： Optimization algorithms

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：