检索结果-内蒙古大学图书馆

A Gradient-Guided Evolutionary Approach to Training Deep Neural Networks

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第9期33卷 4861-4875页

作者： Yang, Shangshang Tian, Ye He, Cheng Zhang, Xingyi Tan, Kay Chen Jin, Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR Department of Computer Science University of Surrey Guildford U.K

It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. The proposed approach suggests a novel genetic operator to optimize the weights in the search space, where the search direction is determined by the gradient of weights. Moreover, the network sparsity is considered in the proposed approach, which highly reduces the network complexity and alleviates overfitting. Experimental results on single-layer NNs, deep-layer NNs, recurrent NNs, and convolutional NNs (CNNs) demonstrate the effectiveness of the proposed approach. In short, this work not only introduces a novel approach for training DNNs but also enhances the performance of EAs in solving large-scale optimization problems.

关键词： Artificial neural networks Training Optimization Search problems Scalability Complexity theory Genetic algorithms Deep neural networks (DNNs) evolutionary algorithm (EA) genetic operator gradient descent sparsity

来源：评论

学校读者我要写书评

暂无评论

DeepPointMap2: Accurate and Robust LiDAR-Visual SLAM with Neural Descriptors 24

DeepPointMap2: Accurate and Robust LiDAR-Visual SLAM with Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Xiaze Ding, Ziheng Jing, Qi Cheng, Ying Ding, Wenchao Feng, Rui Fudan University Shanghai China The School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China The Academy for Engineering and Technology Fudan University China The Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

ISBN: (纸本)9798400706868

Simultaneous Localization and Mapping (SLAM) plays a pivotal role in autonomous driving and robotics. Existing methods often rely on hand-craft feature extraction and cross-modal fusion techniques, resulting in limited feature representation capability and reduced robustness. To address this challenge, we introduce DeepPointMap2, a novel learning-based LiDAR-Visual SLAM architecture that leverages neural descriptors to tackle multiple SLAM sub-tasks in a unified manner. Our approach employs neural networks to extract multi-modal tokens, which are then adaptively fused by the Visual-Point Fusion Module to generate sparse 3D neural descriptors, ensuring precise and robust performance. As a pioneering work, our method achieves state-of-the-art localization performance among various Visual-, LiDAR-, and Visual-LiDAR-based methods in widely-used benchmarks, as shown in the experiment results. Furthermore, the approach proves to be robust in scenarios involving camera failure and LiDAR obstruction. © 2024 ACM.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

A Bi-selection Method Based on Consistent Matrix for Large-Scale Datasets

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1992-2005页

作者： Quan, Jinsheng Qiao, Fengcai Yang, Tian Shen, Shuo Qian, Yuhua Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Institute of Interdisciplinary Studies Changsha410081 China National University of Defense Technology College of Advanced Interdisciplinary Studies Changsha410081 China Shanxi University Institute of Big Data Science and Industry Taiyuan030006 China

Biselection (feature and sample selection) enhances the efficiency and accuracy of machine learning models when handling large-scale data. Fuzzy rough sets, an uncertainty mathematics model known for its excellent interpretability, are widely used in machine learning, particularly for feature selection. While the consistent matrix has significantly improved the computational efficiency and scalability of feature selection, like most fuzzy rough set-based methods, it focuses only on feature selection and seldom incorporates sample selection. This feature-centric approach can limit classification performance, particularly in noisy and large-scale datasets where both features and samples require judicious selection. To overcome these limitations, this article explores the integration of sample selection with feature selection. First, we introduce a β-consistent granulation method to generate more accurate and concise fuzzy information granules, reducing the impact of noisy samples. In addition, a novel membership function is employed to distinguish noise while simultaneously evaluating both features and samples. As a result, a biselection algorithm with linear computation complexity is proposed to select high-quality features and samples. Numerical experiments demonstrate that, compared to eleven representative algorithms, our proposed method achieves an average accuracy improvement of 9.66% and a 933-fold increase in efficiency. © 2025 IEEE.

关键词： Rough sets Noise Feature extraction Classification algorithms Accuracy Machine learning information systems Data models Computational efficiency Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

LRT-DETR: An Enhanced Transformer-Based Framework for PCB Surface Defect Detection

LRT-DETR: An Enhanced Transformer-Based Framework for PCB Su...

引用

Artificial Intelligence, Networking and information Technology (AINIT), International Seminar on

作者： Hongyu Tang Dengli Bu Guanhao Mo Panlin Lu Zhenhai Li Long Huang Key Laboratory of Intelligent Computing and Distributed Information Processing School of Computer Science and Technology Guangxi University of Science and Technology Guangxi Colleges and Universities Liuzhou China

ISBN: (数字)9798331522285

ISBN: (纸本)9798331522292

To address the issues of complex background interference and micro-defect detection in printed circuit board (PCB) surface inspection, while accommodating the deployment constraints of edge devices in industrial scenarios, this paper proposes a lightweight real-time detection Transformer (LRTDETR), an improved architecture based on RT-DETR. First, the original ResNet18 backbone is replaced with RepNCSPELAN, a lightweight network leveraging structural re-parameterization to reduce model complexity. Second, a global-local bidirectional feature pyramid network is introduced in the neck, which enhances the multi-scale feature representation through an adaptive weighted feature fusion mechanism, significantly improving small defect detection. Experimental results demonstrate that the improved model achieves a 96.9% mean average precision (mAP) with only a 0.2% performance drop compared to the baseline. Notably, the model size, the parameters, and the FLOPs are reduced by $58.3 \%, 53.5 \%$ , and 57.3%, respectively. The inference speed reaches 39 FPS, balancing accuracy and efficiency for real-time industrial inspection and edge deployment. This work provides a practical solution for highprecision, resource-efficient defect detection in industrial edge computing environments.

关键词： Adaptation models Computational modeling Image edge detection Printed circuits Inspection Feature extraction Transformers Real-time systems Neck Defect detection

来源：评论

学校读者我要写书评

暂无评论

Monotonicity and nonmonotonicity in L3-valued propositional logic

引用

Frontiers of Computer Science 2022年第4期16卷 33-43页

作者： Wei Li Yuefei Sui State Key Laboratory of Software Development Environment Beihang UniversityBeijing100083China Key Laboratory of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing100049China

A sequent is a pair (Γ, Δ), which is true under an assignment if either some formula in Γ is false, or some formula in Δ is true. In L_(3)-valued propositional logic, a multisequent is a triple Δ∣Θ∣Γ, which is true under an assignment if either some formula in Δ has truth-value t, or some formula in Θ has truth-value m, or some formula in Γ has truth-value f. There is a sound, complete and monotonic Gentzen deduction system G for sequents. Dually, there is a sound, complete and nonmonotonic Gentzen deduction system G′ for co-sequents Δ: Θ: Γ. By taking different quantifiers some or every, there are 8 kinds of definitions of validity of multisequent Δ∣Θ∣Γ and 8 kinds of definitions of validity of co-multisequent Δ: Θ: Γ, and correspondingly there are 8 sound and complete Gentzen deduction systems for sequents and 8 sound and complete Gentzen deduction systems for co-sequents. Correspondingly their monotonicity is discussed.

关键词： sequent mulisequent gentzen deduction system monotonicity nonmonotonicity

来源：评论

学校读者我要写书评

暂无评论

Design of Control Circuit for Active Metasurface Based on Varactor Diode

Design of Control Circuit for Active Metasurface Based on Va...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Zhang, Yue Liu, Yuefei Yang, Guohui Zhang, Kuang Li, Yingsong School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China

ISBN: (纸本)9781733509657

A control circuit for active metasurface based on varactor diode is designed in this paper. By varying the reverse bias voltage on the varactor diode, the designed circuit can regulate the additional phase of the active meta-atoms. The circuit adopts a form of one master and multiple slaves, which can simultaneously control the bias voltage of 960 meta-atoms. Each slave can control up to 64 channels. The control accuracy is 0.04V. The power consumption of a single slave is 160mW. Though experiment verification, the circuit has a good effect in controlling the beam deflection of the metasurface and generating OAM beams. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

A Dual-band Low-profile Quadrifilar-Helix Antenna for Satellite Navigation System

A Dual-band Low-profile Quadrifilar-Helix Antenna for Satell...

引用

2023 IEEE International Workshop on Electromagnetics: Applications and Student Innovation Competition, iWEM 2023

作者： Wang, Jiahong Qi, Junwei Li, Yingsong Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350336740

A new dual-band low-profile quadrifilar-helical antenna (QHA) was presented. The spiral radiation arm of QHA is printed to three circular dielectric plates to reduce the antenna height. In this case, the radiation arm of the lower layer is connected to the feed, and the L-shaped branch is connected to the ground through a 50 ohm resistance. The radiation arm in the middle layer adds branches to realize dual frequency. The upper radiation arm rotates inward and folds, further realizing miniaturization. As a result, the height of QHA is only 20mm. Through CST simulation and optimization, The operating frequency bands of QHA are 1GHz - 1.45GHz and 1.54GHz - 1.74GHz. The beam width of QHA is more than 120°, which is to provide service for satellite navigating systems. The AR for the operation bands are less than 3dB. © 2023 IEEE.

关键词： Satellites

来源：评论

学校读者我要写书评

暂无评论

Adaptive Step-Size Sparse Millimeter Wave Imaging Algorithm Based on Approximate Observations 11

Adaptive Step-Size Sparse Millimeter Wave Imaging Algorithm ...

引用

11th IEEE International Conference on Computer Science and Network Technology, ICCSNT 2023

作者： Wang, Dianhao Huang, Xinqi Yu, Canping Mao, Qi Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350311594

The currently constructed millimeter wave imaging system has the problems of long sampling time and more sampling points of antenna units, and the use of compressed perception algorithm can improve the imaging quality when the number of sampling points are much smaller than the Nyquist distance sampling. The traditional compressed perception algorithm can achieve better sparse recovery than the matched filter imaging algorithm, but there is a large dimension of the measurement matrix and high computational complexity. For the problems of difficult data processing and large dimensions of measurement matrix, a sparse imaging regularization model is constructed based on approximate observation, and an improved soft threshold iterative algorithm is used with adaptive step size, which improves the convergence performance, reduces the computational complexity of the sparse recovery dramatically and achieves a better quality of sparse imaging than the traditional compressed perception algorithm. © 2023 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Affine-Projection Maximum Asymmetric Correntropy Criterion Algorithm Under System Identifications 11

Affine-Projection Maximum Asymmetric Correntropy Criterion A...

引用

11th IEEE International Conference on Computer Science and Network Technology, ICCSNT 2023

作者： Peng, Yan Huang, Xinqi Yu, Canping Mao, Qi Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9798350311594

The Affine-Projection Maximum Asymmetric Correntropy Criterion (APMACC) is constructed, drawing upon the fundamental principles of the maximum asymmetric correntropy criterion and an affine-projection scheme. The APMACC algorithm incorporates the asymmetric Gaussian model as a kernel function within the Affine-Projection (AP) algorithm framework, thereby endowing it with robustness against asymmetrically distributed noise. Furthermore, the bound for step-size is established in the literature. Simulation results demonstrate that the APMACC has fast convergence and low steady-state. © 2023 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Improving Fake News Video Detection by Correlating with Neighbors 61

Improving Fake News Video Detection by Correlating with Neig...

引用

Findings of the Association for Computational Linguistics, ACL 2023

作者： Qi, Peng Zhao, Yuyang Shen, Yufeng Ji, Wei Cao, Juan Chua, Tat-Seng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China National University of Singapore Singapore

ISBN: (纸本)9781959429623

The prevalence of short video platforms has spawned a lot of fake news videos, which have stronger propagation ability than textual fake news. Thus, automatically detecting fake news videos has been an important countermeasure in practice. Previous works commonly verify each news video individually with multimodal information. Nevertheless, news videos from different perspectives regarding the same event are commonly posted together, which contain complementary or contradictory information and thus can be used to evaluate each other mutually. To this end, we introduce a new and practical paradigm, i.e., cross-sample fake news video detection, and propose a novel framework, Neighbor-Enhanced fakE news video Detection (NEED), which integrates the neighborhood relationship of new videos belonging to the same event. NEED can be readily combined with existing single-sample detectors and further enhance their performances with the proposed graph aggregation (GA) and debunking rectification (DR) modules. Specifically, given the feature representations obtained from single-sample detectors, GA aggregates the neighborhood information with the dynamic graph to enrich the features of independent samples. After that, DR explicitly leverages the relationship between debunking videos and fake news videos to refute the candidate videos via textual and visual consistency. Extensive experiments on the public benchmark demonstrate that NEED greatly improves the performance of both single-modal (up to 8.34% in accuracy) and multimodal (up to 4.97% in accuracy) base detectors. Codes are available in https://***/ICTMCG/NEED. © 2023 Association for Computational Linguistics.

关键词： Benchmarking

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：