检索结果-内蒙古大学图书馆

4th IFIP TC 12 International Conference on Intelligence science, ICIS 2020

作者： Wang, Dong-Sheng Zhao, Cui-Ping Wang, Qi Ofori, Kwame Dwomoh Han, Bin Liu, Ga-Qiong Wang, Shi Wang, Hua-Yu Zhang, Jing School of Computer Science Jiangsu University of Science of Technology Zhenjiang Jiangsu212001 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Army Engineering University Nanjing Jiangsu210007 China

ISBN: (纸本)9783030748258

Sentence similarity calculation is one of several research topics in natural language processing. It has been widely used in information retrieval, intelligent question answering and other fields. Traditional machine learning methods generally extract sentence features through manually defined feature templates and then perform similarity calculations. This type of method usually requires more human intervention and constantly has to deal with domain migration problems. Automatically extracting sentence features using certain deep learning algorithms helps to solve domain migration problems. The training data is of the domain is required to complete the extraction process. However, the neural network structure design in the deep learning model usually requires experienced experts to carry out multiple rounds of the tuning design phase. Using an automatic neural architecture search (ANAS) technology deals with all the network structure design problems. This paper proposes a sentence similarity calculation method based on neural architecture search. This method uses a combination of grid search and random search. The method in this paper is tested on the Quora "Question-Pairs" data set and has an accuracy of 81.8%. The experimental results show that the method proposed in this paper can efficiently and automatically learn the network structure of the deep learning model to achieve high accuracy. © 2021, IFIP International Federation for information processing.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

TS-ENAS:Two-Stage Evolution for Cell-based Network Architecture Search

arXiv

引用

arXiv 2023年

作者： Zou, Juan Wu, Shenghong Xia, Yizhang Jiang, Weiwei Wu, Zeping Zheng, Jinhua Engineering Research Center of Hunan Province for Optimization and Security of Intelligent System Key Laboratory of Intelligent Computing and Information Processing Ministry of Education of China Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan University Hunan Province Xiangtan411105 China The College of Aerospace Science and Engineering National University of Defense Technology Hunan Changsha410073 China

Neural network architecture search provides a solution to the automatic design of network structures. However, it is difficult to search the whole network architecture directly. Although using stacked cells to search neural network architectures is an effective way to reduce the complexity of searching, these methods do not able find the global optimal neural network structure since the number of layers, cells and connection methods is fixed. In this paper, we propose a Two-Stage Evolution for cell-based Network Architecture Search(TS-ENAS), including one-stage searching based on stacked cells and second-stage adjusting these cells. In our algorithm, a new cell-based search space and an effective two-stage encoding method are designed to represent cells and neural network structures. In addition, a cell-based weight inheritance strategy is designed to initialize the weight of the network, which significantly reduces the running time of the algorithm. The proposed methods are extensively tested and compared on four image classification dataset, Fashion-MNIST, CIFAR10, CIFAR100 and ImageNet and compared with 22 state-of-the-art algorithms including hand-designed networks and NAS networks. The experimental results show that TS-ENAS can more effectively find the neural network architecture with comparative performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Paired 2-Disjoint Path Covers of Burnt Pancake Graphs with Faulty Elements

SSRN

引用

SSRN 2024年

作者： Li, Pingshan Chen, Congzhen Liu, Xianglin Xiangtan University China School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China Key Laboratory of Intelligent Computing & Information Processing of Education China Key Laboratory for Computation and Simulation in Science and Engineering China National Center for Applied Mathematics in Hunan China Guangxi Vocational University of Agriculture Guangxi Nanning530007 China

It is a key issue in parallel processing to find $k$-disjoint paths in the underlying graph of an interconnected network such that these disjoint paths pass through all vertices of the network, this is known as paired $k$-disjoint path cover problems or unpaired $k$-disjoint path cover problems. In 2024, Dvo\v{r}\'{a}k and Gu (Theoretical Computer science, $986 (2024) 114327$) showed that there exist two disjoint paths whose vertices partition the vertex of the burnt pancake graph even if it contains at most $n-4$ faulty elements (vertices or edges) and they proposed an open problem: is it possible to improve the upper bound $n-4$ to $n-3$? In this paper, we provide a positive answer to this problem. © 2024, The Authors. All rights reserved.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing

arXiv

引用

arXiv 2023年

作者： Chen, Zhaoliang Wu, Zhihao Lin, Zhenghong Wang, Shiping Plant, Claudia Guo, Wenzhong The College of Computer and Data Science Fuzhou University Fuzhou350116 China The Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China The Faculty of Computer Science Austria The research network Data Science @ Uni Vienna University of Vienna Vienna1090 Austria

Graph Convolutional Network (GCN) with the powerful capacity to explore graph-structural data has gained noticeable success in recent years. Nonetheless, most of the existing GCN-based models suffer from the notorious over-smoothing issue, owing to which shallow networks are extensively adopted. This may be problematic for complex graph datasets because a deeper GCN should be beneficial to propagating information across remote neighbors. Recent works have devoted effort to addressing over-smoothing problems, including establishing residual connection structure or fusing predictions from multi-layer models. Because of the indistinguishable embeddings from deep layers, it is reasonable to generate more reliable predictions before conducting the combination of outputs from various layers. In light of this, we propose an Alternating Graph-regularized Neural Network (AGNN) composed of Graph Convolutional Layer (GCL) and Graph Embedding Layer (GEL). GEL is derived from the graph-regularized optimization containing Laplacian embedding term, which can alleviate the over-smoothing problem by periodic projection from the low-order feature space onto the high-order space. With more distinguishable features of distinct layers, an improved Adaboost strategy is utilized to aggregate outputs from each layer, which explores integrated embeddings of multi-hop neighbors. The proposed model is evaluated via a large number of experiments including performance comparison with some multi-layer or multi-order graph neural networks, which reveals the superior performance improvement of AGNN compared with state-of-the-art models. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Adjusting Dynamics of Hopfield Neural Network via Time-variant Stimulus

arXiv

引用

arXiv 2024年

作者： Peng, Xuenan Li, Chengqing Zeng, Yicheng Li, Chun-Lai School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China Key Laboratory of Intelligent Computing & Information Processing the Ministry of Education Xiangtan University Hunan Xiangtan411105 China School of Physics and Optoelectronic Engineering Xiangtan University Hunan Xiangtan411105 China School of Computer Science Xiangtan University Hunan Xiangtan411105 China

As a paradigmatic model for nonlinear dynamics studies, the Hopfield Neural Network (HNN) demonstrates a high susceptibility to external disturbances owing to its intricate structure. This paper delves into the challenge of modulating HNN dynamics through time-variant stimuli. The effects of adjustments using two distinct types of time-variant stimuli, namely the Weight Matrix Stimulus (WMS) and the State Variable Stimulus (SVS), along with a Constant Stimulus (CS) are reported. The findings reveal that deploying four WMSs enables the HNN to generate either a four-scroll or a coexisting two-scroll attractor. When combined with one SVS, four WMSs can lead to the formation of an eight-scroll or four-scroll attractor, while the integration of four WMSs and multiple SVSs can induce grid-multi-scroll attractors. Moreover, the introduction of a CS and an SVS can significantly disrupt the dynamic behavior of the HNN. Consequently, suitable adjustment methods are crucial for enhancing the network’s dynamics, whereas inappropriate applications can lead to the loss of its chaotic characteristics. To empirically validate these enhancement effects, the study employs an FPGA hardware platform. Subsequently, an image encryption scheme is designed to demonstrate the practical application benefits of the dynamically adjusted HNN in secure multimedia communication. This exploration into the dynamic modulation of HNN via time-variant stimuli offers insightful contributions to the advancement of secure communication *** Codes 68T07 Copyright © 2024, The Authors. All rights reserved.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

ObjectFormer for Image Manipulation Detection and Localization

arXiv

引用

arXiv 2022年

作者： Wang, Junke Wu, Zuxuan Chen, Jingjing Han, Xintong Shrivastava, Abhinav Lim, Ser-Nam Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Huya Inc University of Maryland United States Meta AI

Recent advances in image editing techniques have posed serious challenges to the trustworthiness of multimedia data, which drives the research of image tampering detection. In this paper, we propose ObjectFormer to detect and localize image manipulations. To capture subtle manipulation traces that are no longer visible in the RGB domain, we extract high-frequency features of the images and combine them with RGB features as multimodal patch embeddings. Additionally, we use a set of learnable object prototypes as mid-level representations to model the object-level consistencies among different regions, which are further used to refine patch embeddings to capture the patch-level consistencies. We conduct extensive experiments on various datasets and the results verify the effectiveness of the proposed method, outperforming state-of-the-art tampering detection and localization methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction of Bearing via a Double Attention-Based Deep Neural Network

Remaining Useful Life Prediction of Bearing via a Double Att...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted computing, UIC-ATC

作者： Yongkang Liu Donghui Pan Haifeng Zhang Kai Zhong Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical Science Anhui University Hefei Anhui China Institutes of Physical Science and Information Technology Anhui University Hefei Anhui China

Predicting the remaining useful life (RUL) of bearings is important for the secure running and reducing maintenance costs of rotating machinery. In this article, a novel feature extraction and RUL prediction framework of bearing is proposed by utilizing time-frequency representations (TFRs) and deep neural network with double attention (DA-DNN). Firstly, TFRs are employed to extract the degradation features associated with RUL prediction, which can effectively cope with the non-stationary properties of bearing vibration data. The reduced dimensional TFRs are then used as the DA-DNN model input. Afterwards, DA-DNN is developed by employing the double attention structure to extract the key degradation features more efficiently. The dual-attention structure has ability to capture the degradationrelated features from two aspects of channel attention and spatial attention, which enables the network to focus on high RUL-relevant information. Finally, the experimental results demonstrate the effectiveness of DA-DNN, which shows higher performance in terms of prediction accuracy compared to other deep learning (DL) methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A C0-continuous nonconforming virtual element method for linear strain gradient elasticity

arXiv

引用

arXiv 2024年

作者： Huang, Jianguo Yu, Yue School of Mathematical Sciences MOE-LSC Shanghai Jiao Tong University Shanghai200240 China Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education National Center for Applied Mathematics in Hunan School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

A robust C0-continuous nonconforming virtual element method (VEM) is developed for a boundary value problem arising from strain gradient elasticity in two dimensions, with the family of polygonal meshes satisfying a very general geometric assumption given in Brezzi et al. (2009) and Chen and Huang (2018). The stability condition of the VEMs is derived by establishing Korn-type inequalities and inverse inequalities. Some crucial commutative relations for locking-free analysis as in elastic problems are derived. The sharp and uniform error estimates with respect to both the microscopic parameter and the Lamé coefficient are achieved in the lowest-order case, which is also verified by numerical *** Codes 65N12, 65N15, 65N22, 65N30 © 2024, CC BY-NC-ND.

关键词： Boundary value problems

来源：评论

学校读者我要写书评

暂无评论

Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection

arXiv

引用

arXiv 2024年

作者： Liang, Hanzhe Xie, Guoyang Hou, Chengbin Wang, Bingshu Gao, Can Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Audencia Financial Technology Institute Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Intelligent Manufacturing CATL Ningde China School of Computing and Artificial Intelligence Fuyao University of Science and Technology Fuzhou China School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we introduce a straightforward method named Internal Spatial Modality Perception (ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine (SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction module for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further aligning precise spatial structure. Extensive experiments validate the effectiveness of our proposed method, achieving object-level and pixel-level AUROC improvements of 4.2% and 13.1%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and is verified in both classification and segmentation tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Modality-Aware Contrastive Instance Learning with Self-Distillation forWeakly-Supervised Audio-Visual Violence Detection

arXiv

引用

arXiv 2022年

作者： Yu, Jiashuo Liu, Jinyu Cheng, Ying Feng, Rui Zhang, Yuejie School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Academy for Engineering and Technology Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China

Weakly-supervised audio-visual violence detection aims to distinguish snippets containing multimodal violence events with video-level labels. Many prior works perform audio-visual integration and interaction in an early or intermediate manner, yet overlooking the modality heterogeneousness over the weakly-supervised setting. In this paper, we analyze the modality asynchrony and undifferentiated instances phenomena of the multiple instance learning (MIL) procedure, and further investigate its negative impact on weakly-supervised audio-visual learning. To address these issues, we propose a modality-aware contrastive instance learning with self-distillation (MACIL-SD) strategy. Specifically, we leverage a lightweight two-stream network to generate audio and visual bags, in which unimodal background, violent, and normal instances are clustered into semi-bags in an unsupervised way. Then audio and visual violent semi-bag representations are assembled as positive pairs, and violent semi-bags are combined with background and normal instances in the opposite modality as contrastive negative pairs. Furthermore, a self-distillation module is applied to transfer unimodal visual knowledge to the audio-visual model, which alleviates noises and closes the semantic gap between unimodal and multimodal features. Experiments show that our framework outperforms previous methods with lower complexity on the large-scale XD-Violence dataset. Results also demonstrate that our proposed approach can be used as plug-in modules to enhance other networks. Codes are available at https://***/JustinYuu/MACIL-SD. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

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：