检索结果-内蒙古大学图书馆

Defect detection of gear parts in virtual manufacturing

Visual Computing for Industry,Biomedicine,and Art 2023年第1期6卷 76-87页

作者： Zhenxing Xu Aizeng Wang Fei Hou Gang Zhao School of Mechanical Engineering&Automation Beihang UniversityBeijing 100191China State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Gears play an important role in virtual manufacturing systems for digital twins;however,the image of gear tooth defects is difficult to acquire owing to its non-convex *** this study,a deep learning network is proposed to detect gear defects based on their point cloud *** approach mainly consists of three steps:(1)Various types of gear defects are classified into four cases(fracture,pitting,glue,and wear);A 3D gear dataset was constructed with 10000 instances following the aforementioned classification.(2)Gear-PCNet++introduces a novel Combinational Convolution Block,proposed based on the gear dataset for gear defect detection to effectively extract the local gear information and identify its complex topology;(3)Compared with other methods,experiments show that this method can achieve better recognition results for gear defects with higher efficiency and practicability.

关键词： Defect detection Gear surface Gear dataset Combinational Convolution Block

来源：评论

学校读者我要写书评

暂无评论

RVFC: RISC-V Formal in Chisel

RVFC: RISC-V Formal in Chisel

引用

2023 International Symposium of Electronics Design Automation, ISEDA 2023

作者： Xiang, Mufan Li, Yongjian Zhao, Yongxin East China Normal University Shanghai Key Laboratory of Trustworthy Computing Shanghai China Institute of Software Chinese Academy of Sciences State Key Laboratory of Computer Science Beijing China

ISBN: (纸本)9798350304510

With the increasing complexity of hardware design requirements and the development of open-source hardware ecosystems, Chisel and RISC-V are becoming increasingly popular. As a domain-specific language of Scala, Chisel is gradually becoming the choice of hardware design development with the help of the features of high-level languages. Especially in the RISC-V open-source instruction set ecosystem, many representative projects are implemented with Chisel. In hardware development, the correctness verification of the design is essential. A promising stream for verifying the correctness of RISC-V designs is RISC-V Formal, which is at the SystemVerilog level. In this paper, we propose RVFC, a framework for formal verification of RISC-V designs at the Chisel level. It is based on the ability of ChiselFV to define formal properties and verify them at the Chisel level. We also reimplemented a textbook RISC-V five-stage pipeline design and found an oversight in the design through RVFC verification. © 2023 IEEE.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

Generalizability of Memorization Neural Networks 38

Generalizability of Memorization Neural Networks

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yu, Lijia Gao, Xiao-Shan Zhang, Lijun Miao, Yibo State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

The neural network memorization problem is to study the expressive power of neural networks to interpolate a finite dataset. Although memorization is widely believed to have a close relationship with the strong generalizability of deep learning when using over-parameterized models, to the best of our knowledge, there exists no theoretical study on the generalizability of memorization neural networks. In this paper, we give the first theoretical analysis of this topic. Since using i.i.d. training data is a necessary condition for a learning algorithm to be generalizable, memorization and its generalization theory for i.i.d. datasets are developed under mild conditions on the data distribution. First, algorithms are given to construct memorization networks for an i.i.d. dataset, which have the smallest number of parameters and even a constant number of parameters. Second, we show that, in order for the memorization networks to be generalizable, the width of the network must be at least equal to the dimension of the data, which implies that the existing memorization networks with an optimal number of parameters are not generalizable. Third, a lower bound for the sample complexity of general memorization algorithms and the exact sample complexity for memorization algorithms with constant number of parameters are given. It is also shown that there exist data distributions such that, to be generalizable for them, the memorization network must have an exponential number of parameters in the data dimension. Finally, an efficient and generalizable memorization algorithm is given when the number of training samples is greater than the efficient memorization sample complexity of the data distribution. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-shot Named Entity Recognition via Superposition Concept Discrimination 30

Few-shot Named Entity Recognition via Superposition Concept ...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Chen, Jiawei Lin, Hongyu Han, Xianpei Lu, Yaojie Jiang, Shanshan Dong, Bin Sun, Le Chinese Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Ricoh Software Research Center Beijing Co. Ltd. China

ISBN: (纸本)9782493814104

Few-shot NER aims to identify entities of target types with only limited number of illustrative instances. Unfortunately, few-shot NER is severely challenged by the intrinsic precise generalization problem, i.e., it is hard to accurately determine the desired target type due to the ambiguity stemming from information deficiency. In this paper, we propose Superposition Concept Discriminator (SuperCD), which resolves the above challenge via an active learning paradigm. Specifically, a concept extractor is first introduced to identify superposition concepts from illustrative instances, with each concept corresponding to a possible generalization boundary. Then a superposition instance retriever is applied to retrieve corresponding instances of these superposition concepts from large-scale text corpus. Finally, annotators are asked to annotate the retrieved instances and these annotated instances together with original illustrative instances are used to learn FS-NER models. To this end, we learn a universal concept extractor and superposition instance retriever using a large-scale openly available knowledge bases. Experiments show that SuperCD can effectively identify superposition concepts from illustrative instances, retrieve superposition instances from large-scale corpus, and significantly improve the few-shot NER performance with minimal additional efforts. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： active learning few-shot learning named entity recognition

来源：评论

学校读者我要写书评

暂无评论

Poster Abstract: Ripple: Large-Scale Service and Configuration Management in the Cloud 25

Poster Abstract: Ripple: Large-Scale Service and Configurati...

引用

25th ACM International Middleware Conference Demos, Posters and Doctoral Symposium, MIDDLEWARE 2024

作者： Ji, Shuping Tang, Zhen Wang, Wei Li, Hui Yao, Jianguo Jacobsen, Hans-Arno Institute of Software Chinese Academy of Sciences Beijing China Shanghai Jiao Tong University Jinan Inspur Data Technology Co. Ltd Shanghai China University of Toronto Toronto Canada Key Laboratory of System Software CAS State Key Laboratory of Computer Science Institute of Software at CAS University of CAS Beijing China University of CAS Nanjing College Nanjing China Nanjing Institute of Software Technology Nanjing China

ISBN: (纸本)9798400713545

Microservice architectures backed by container technology have been widely used in many real-world cloud-native applications. The number of containers in cloud data centers continues to increase, expected to reach several million soon. At this scale, existing service and configuration management solutions have limited efficiency, scalability and robustness. To overcome these limitations, we propose Ripple, which uniquely combines several existing and some novel features including consistent hashing-based workload distribution, dynamic destination list-based and client-assisted message delivery, incremental update, and adaptive load balancing. The experiments show that our solution greatly outperforms its counterparts. © 2024 Copyright held by the owner/author(s).

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Topology-Aware Self-Adaptive Resource Provisioning for Microservices

Topology-Aware Self-Adaptive Resource Provisioning for Micro...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Zeng, Hao Wang, Tao Li, An Wu, Yuewen Wu, Heng Zhang, Wenbo University of Chinese Academy of Sciences Beijing100190 China Institute of Software Chinese Academy of Sciences Beijing100190 China Institute of Software Chinese Academy of Sciences State Key Laboratory of Computer Science Beijing100190 China

ISBN: (纸本)9798350304855

Microservice architecture is a popular technology for deploying services in cloud computing, with benefits like loose coupling, high fault tolerance, and scalability. The heterogeneous resource requirements and complex interaction relations have increased the difficulty in provisioning resources for microservices with intricacy topology. Existing approaches allocate resources for different microservices separately, and thus cannot achieve optimal global performance. Moreover, these approaches extract features from specific microservice topologies. We propose a topology-aware self-adaptive resource provisioning approach for microservices. Firstly, we propose a microservice state graph to characterize the status of each microservice in an application. Then, we use graph neural networks and attention to extract the resource requirements and correlation features of microservices. Thirdly, we use a reinforcement learning-based approach to allocate resources for microservices uniformly. Finally, we evaluate our approach by conducting a series of experiments on three typical microservice applications deployed in a heterogeneous cluster. The results show that our approach is efficient in extracting resource and correlation features of microservices, and can guarantee QoS with efficient resource utilization. Our approach can reduce the End-to-End latency by 22%, and can improve resource utilization by 18% with guaranteed latency. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Light field super-resolution using complementary-view feature attention

引用

Computational Visual Media 2023年第4期9卷 843-858页

作者： Wei Zhang Wei Ke Da Yang Hao Sheng Zhang Xiong Faculty of Applied Sciences Macao Polytechnic UniversityMacao SAR 999078China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191Chinaand Beihang Hangzhou Innovation Institute YuhangXixi Octagon CityYuhang DistrictHangzhou 310023China

Light field(LF)cameras record multiple perspectives by a sparse sampling of real scenes,and these perspectives provide complementary *** information is beneficial to LF super-resolution(LFSR).Compared with traditional single-image super-resolution,LF can exploit parallax structure and perspective correlation among different LF ***,the performance of existing methods are limited as they fail to deeply explore the complementary information across LF *** this paper,we propose a novel network,called the light field complementary-view feature attention network(LF-CFANet),to improve LFSR by dynamically learning the complementary information in LF ***,we design a residual complementary-view spatial and channel attention module(RCSCAM)to effectively interact with complementary information between complementary ***,RCSCAM captures the relationships between different channels,and it is able to generate informative features for reconstructing LF images while ignoring redundant ***,a maximum-difference information supplementary branch(MDISB)is used to supplement information from the maximum-difference angular positions based on the geometric structure of LF *** branch also can guide the process of *** results on both synthetic and real-world datasets demonstrate the superiority of our *** proposed LF-CFANet has a more advanced reconstruction performance that displays faithful details with higher SR accuracy than state-of-the-art methods.

关键词： light field(LF) super-resolution(SR) attention

来源：评论

学校读者我要写书评

暂无评论

Design space exploration of neural network accelerator based on transfer learning

引用

High Technology Letters 2023年第4期29卷 416-426页

作者：吴豫章 ZHI Tian SONG Xinkai LI Xi School of Computer Science University of Science and Technology of ChinaHefei 230027P.R.China State Key Lab of Processors Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190P.R.China

With the increasing demand of computational power in artificial intelligence(AI)algorithms,dedicated accelerators have become a ***,the complexity of hardware architectures,vast design search space,and complex tasks of accelerators have posed significant ***-ditional search methods can become prohibitively slow if the search space continues to be expanded.A design space exploration(DSE)method is proposed based on transfer learning,which reduces the time for repeated training and uses multi-task models for different tasks on the same *** proposed method accurately predicts the latency and energy consumption associated with neural net-work accelerator design parameters,enabling faster identification of optimal outcomes compared with traditional *** compared with other DSE methods by using multilayer perceptron(MLP),the required training time is *** experiments with other methods demonstrate that the proposed method improves the efficiency of DSE without compromising the accuracy of the re-sults.

关键词： design space exploration(DSE) transfer learning neural network accelerator multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Pattern Shifting or Knowledge Losing? A Forgetting Perspective for Understanding the Effect of Instruction Fine-Tuning 23rd

Pattern Shifting or Knowledge Losing? A Forgetting Perspect...

引用

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Zhang, Chunkang Cao, Boxi Lu, Yaojie Lin, Hongyu Cao, Liu Zeng, Ke Wan, Guanglu Cai, Xunliang Han, Xianpei Sun, Le Chinese Information Processing Laboratory Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Meituan Beijing China

ISBN: (纸本)9789819783663

Instruction Fine-Tuning (IFT) emerges as an essential step of training large language models to robustly carry out tasks of interest. However, there lacks a systematic investigation about the underlying mechanisms of instruction fine-tuning, particularly on the forgetting phenomenon after IFT, known as alignment tax. Therefore, to understand the mechanism of IFT from the forgetting perspective, we investigate the alternation of the text pattern and knowledge within models throughout the entire IFT process. Specifically, we restore fine-tuned models to their base version by training them on the data sharing a similar distribution with the pre-training corpus and compare their results Our experiment indicates that there is a stage transition of forgetting during IFT process: (1) Pseudo Forgetting: in this stage, models mainly shift their familiar text pattern away from pre-training data format while the world knowledge is preserved. Consequently, models will recover to their original performance when they are restored to the base version. (2) Actual Forgetting: in this stage, models forget the acquired knowledge as well. Therefore, they fail to reach the original performance even if they are restored to the base version. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

From Transparent to Opaque: Rethinking Neural Implicit Surfaces with α-NeuS 38

From Transparent to Opaque: Rethinking Neural Implicit Surfa...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Haoran Deng, Junkai Chen, Xuhui Hou, Fei Wang, Wencheng Qin, Hong Qian, Chen He, Ying State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China University of Chinese Academy of Sciences China College of Computing and Data Science Nanyang Technological University Singapore Department of Computer Science Stony Brook University United States SenseTime Research Hong Kong

Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. Recent advances in neural radiance fields and its variants primarily address opaque or transparent objects, encountering difficulties to reconstruct both transparent and opaque objects simultaneously. This paper introduces α-NeuS-an extension of NeuS-that proves NeuS is unbiased for materials from fully transparent to fully opaque. We find that transparent and opaque surfaces align with the non-negative local minima and the zero iso-surface, respectively, in the learned distance field of NeuS. Traditional iso-surfacing extraction algorithms, such as marching cubes, which rely on fixed iso-values, are ill-suited for such data. We develop a method to extract the transparent and opaque surface simultaneously based on DCUDF. To validate our approach, we construct a benchmark that includes both real-world and synthetic scenes, demonstrating its practical utility and effectiveness. Our data and code are publicly available at https://***/728388808/alpha-NeuS. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：