检索结果-内蒙古大学图书馆

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Xiansong Fang Lingjun Zhou Yixiao Zhu Jiayu Zheng Xiang Cai Fan Zhang State Key Laboratory of Advanced Optical Communication System and Networks School of Electronics Peking University Beijing China School of Electronic and Computer Engineering Peking University Shenzhen China State Key Laboratory of Advanced Optical Communication System and Networks Shanghai Jiao Tong University Shanghai China Pengcheng Laboratory Shenzhen China

We experimentally demonstrate the combination of learned modified DBP and adaptive equalizer to compensate for intra- and inter-channel nonlinearity, in an $8\times 125\text{Gbaud}$ 16QAM system over 1600km SSMF, sh...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Next-generation machine vision systems incorporating two-dimensional materials: Progress and perspectives

引用

InfoMat 2022年第1期4卷 23-39页

作者： Peisong Wu Ting He He Zhu Yang Wang Qing Li Zhen Wang Xiao Fu Fang Wang Peng Wang Chongxin Shan Zhiyong Fan Lei Liao Peng Zhou Weida Hu State Key Laboratory of Infrared Physics Shanghai Institute of Technical PhysicsChinese Academy of SciencesShanghaiChina University of Chinese Academy of Sciences BeijingChina Hangzhou Institute for Advanced Study University of Chinese Academy of SciencesHangzhouChina State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghaiChina Henan Key Laboratory of Diamond Optoelectronic Materials and Devices School of Physics and EngineeringZhengzhou UniversityZhengzhouChina Department of Electronic and Computer Engineering The Hong Kong University of Science and TechnologyClear Water BayKowloonHong Kong SARChina School of Physics and Electronics Hunan UniversityChangshaChina

Machine vision systems(MVSs)are an important component of intelligent systems,such as autonomous vehicles and ***,with the continuous increase in data and new application scenarios,new requirements are put forward for the next generation of *** is an urgent need to find new material systems to complement the existing semiconductor technology based on thin-film materials,and new architectures must be explored to improve *** of their unique physical properties,two-dimensional(2D)materials have received extensive attention for use in MVSs,especially in biomimetic ones:the human visual system,which can process complex visual information with low power consumption,provides a model for next-generation *** review paper summarizes the progress and challenges of applying 2D material photodetectors in sense-memory-computational integration and biomimetic image sensors for machine vision.

关键词： in-sensor computing machine vision systems photodetectors two-dimensional materials

来源：评论

学校读者我要写书评

暂无评论

User-level failure detection and auto-recovery of parallel programs in HPC systems

引用

Frontiers of computer Science 2021年第6期15卷 31-42页

作者： Guozhen ZHANG Yi LIU Hailong YANG Jun XU Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China Sino-German Joint Software Institute Beihang UniversityBeijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China Science and Technology on Space System Simulation Laboratory Beijing Simulation Center Beijing 100854China

As the mean-time-between-failures(MTBF)continues to decline with the increasing number of components on large-scale high performance computing(HPC)systems,program failures might occur during the execution period with high *** successful execution of the HPC programs has become an issue that the unprivileged users should be *** the user perspective,if the program failure cannot be detected and handled in time,it would waste resources and delay the progress of program ***,the unprivileged users are unable to perform program state checking due to execution control by the job management system as well as the limited ***,automated tools for supporting user-level failure detection and autorecovery of parallel programs in HPC systems are *** paper proposes an innovative method for the unprivileged user to achieve failure detection of job execution and automatic resubmission of failed *** state checker in our method is encapsulated as an independent job to reduce interference with the user *** addition,we propose a dual-checker mechanism to improve the robustness of our *** implement the proposed method as a tool named automatic re-launcher(ARL)and evaluate it on the Tianhe-2 *** results show that ARL can detect the execution failures effectively on Tianhe-2 *** addition,the communication and performance overhead caused by ARL is *** good scalability of ARL makes it applicable for large-scale HPC systems.

关键词： high performance computing parallel program failure detection failure auto-recovery

来源：评论

学校读者我要写书评

暂无评论

PAM-4 optical transmission beyond 224 Gbps based on an ultrahigh-bandwidth slow-light silicon modulator

PAM-4 optical transmission beyond 224 Gbps based on an ultra...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Han, Changhao Qin, Jun Yang, Qipeng Zheng, Zhao Shu, Haowen Zhang, Yunhao Wu, Yichen Sun, Yu Lu, Junde Zhou, Yan Ge, Zhangfeng Wang, Lei He, Zhixue Yu, Shaohua Hu, Weiwei Peng, Chao Bowers, John E. Wang, Xingjun State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing100192 China Frontiers Science Center for Nano-Optoelectronics Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China Peking University Yangtze Delta Institute of Optoelectronics Nantong226010 China

We experimentally demonstrate PAM-4 optical transmission beyond 224 Gbps based on an ultrahigh-bandwidth slow-light silicon modulator in C-band with the combination of the artificial neural network equalizers. CLEO 20... 详细信息

ISBN: (纸本)9781957171395

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm 29

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

29th IEEE International Conference on Parallel and Distributed systems, ICPADS 2023

作者： Zeng, Yan Huang, Chengchuang Ni, Yijie Zhou, Chunbao Zhang, Jilin Wang, Jue Zhou, Mingyao Xue, Meiting Zhang, Yunquan Hangzhou Dianzi University School of Computer Science and Technology Hangzhou310018 China Ministry of Education Key Laboratory for Modeling and Simulation of Complex Systems Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Hangzhou Dianzi University School of ITMO Joint Institute Hangzhou310018 China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing100086 China HuaWei China Institute of Computing Technology of the Chinese Academy of Sciences State Key Laboratory of Computer Architecture Beijing100086 China

ISBN: (纸本)9798350330717

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network's dataflow graph and device cluster's topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method. © 2023 IEEE.

关键词： Auto-Parallel Distributed machine learning Genetic algorithm Integer linear programming Model parallelism

来源：评论

学校读者我要写书评

暂无评论

Learning or Self-aligning? Rethinking Instruction Fine-tuning

arXiv

引用

arXiv 2024年

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

Instruction Fine-tuning (IFT) is a crucial phase in building large language models (LLMs). Previous works mainly focus on the IFT's role in the transfer of behavioral norms and the learning of additional world knowledge. However, the understanding of the underlying mechanisms of IFT remains significantly limited. In this paper, we design a knowledge intervention framework to decouple the potential underlying factors of IFT, thereby enabling individual analysis of different factors. Surprisingly, our experiments reveal that attempting to learn additional world knowledge through IFT often struggles to yield positive impacts and can even lead to markedly negative effects. Further, we discover that maintaining internal knowledge consistency before and after IFT is a critical factor for achieving successful IFT. Our findings reveal the underlying mechanisms of IFT and provide robust support for some very recent and potential future works. We release our experimental dataset and codes to facilitate future work. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fake Audio Detection with Low-Rank Model Squeezing

Adaptive Fake Audio Detection with Low-Rank Model Squeezing

引用

2023 Workshop on Deepfake Audio Detection and Analysis, DADA 2023

作者： Zhang, Xiaohui Yi, Jiangyan Tao, Jianhua Wang, Chenglong Xu, Le Fu, Ruibo State Key Laboratory of Multimodal Artificial Intelligence System Institute of Automation Chinese Academy of Sciences China School of Computer and Information Technology Beijing Jiaotong University China University of Science and Technology of China China Department of Automation Tsinghua University China School of Artificial Intelligence University of Chinese Academy of Sciences China

The rapid advancement of spoofing algorithms necessitates the development of robust detection methods capable of accurately identifying emerging fake audio. Traditional approaches, such as finetuning on new datasets containing these novel spoofing algorithms, are computationally intensive and pose a risk of impairing the acquired knowledge of known fake audio types. To address these challenges, this paper proposes an innovative approach that mitigates the limitations associated with finetuning. We introduce the concept of training low-rank adaptation matrices tailored specifically to the newly emerging fake audio types. During the inference stage, these adaptation matrices are combined with the existing model to generate the final prediction output. Extensive experimentation is conducted to evaluate the efficacy of the proposed method. The results demonstrate that our approach effectively preserves the prediction accuracy of the existing model for known fake audio types. Furthermore, our approach offers several advantages, including reduced storage memory requirements and lower equal error rates compared to conventional finetuning methods, particularly on specific spoofing algorithms. © 2023 CEUR-WS. All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEs

arXiv

引用

arXiv 2024年

作者： Han, Xi Hou, Fei Qin, Hong Stony BrookNY11794 United States Key Laboratory of System Software Chinese Academy of Sciences State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Numerical solvers of Partial Differential Equations (PDEs) are of fundamental significance to science and engineering. To date, the historical reliance on legacy techniques has circumscribed possible integration of big data knowledge and exhibits sub-optimal efficiency for certain PDE formulations, while data-driven neural methods typically lack mathematical guarantee of convergence and correctness. This paper articulates a mathematically rigorous neural solver for linear PDEs. The proposed UGrid solver, built upon the principled integration of U-Net and MultiGrid, manifests a mathematically rigorous proof of both convergence and correctness, and showcases high numerical accuracy, as well as strong generalization power to various input geometry/values and multiple PDE formulations. In addition, we devise a new residual loss metric, which enables self-supervised training and affords more stability and a larger solution space over the legacy losses. © 2024, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalizability of Memorization Neural Networks

arXiv

引用

arXiv 2024年

作者： Yu, Lijia Gao, Xiao-Shan Zhang, Lijun Miao, Yibo Key Laboratory of System Software CAS 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, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Boosting the Restoring Performance of Deduplication Data by Classifying Backup Metadata

引用

ACM/IMS Transactions on Data Science 2021年第2期2卷 1–16页

作者： Yang, Ru Deng, Yuhui Zhou, Yi Huang, Ping Department of Computer Science Jinan University Guangzhou510632 China Department of Computer Science Jinan University China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China TSYS School of Computer Science Columbus State University Doimukh Georgia College of Engineering Temple University United States

Restoring data is the main purpose of data backup in storage systems. The fragmentation issue, caused by physically scattering logically continuous data across a variety of disk locations, poses a negative impact on the restoring performance of a deduplication system. Rewriting algorithms are used to alleviate the fragmentation problem by improving the restoring speed of a deduplication system. However, rewriting methods give birth to a big sacrifice in terms of deduplication ratio, leading to a huge storage space waste. Furthermore, traditional backup approaches treat file metadata and chunk metadata as the same, which causes frequent on-disk metadata accesses. In this article, we start by analyzing storage characteristics of backup metadata. An intriguing finding shows that with 10 million files, the file metadata merely takes up approximately 340 MB. Motivated by this finding, we propose a Classified-Metadata based Restoring method (CMR) that classifies backup metadata into file metadata and chunk metadata. Because the file metadata merely takes up a meager amount of space, CMR maintains all file metadata in memory, whereas chunk metadata are aggressively prefetched to memory in a greedy manner. A deduplication system with CMR in place exhibits three salient features: (i) It avoids rewriting algorithms' additional overhead by reducing the number of disk reads in a restoring process, (ii) it increases the restoring throughput without sacrificing the deduplication ratio, and (iii) it thoroughly leverages the hardware resources to boost the restoring performance. To quantitatively evaluate the performance of CMR, we compare our CMR against two state-of-the-art approaches, namely, a history-aware rewriting method (HAR) and a context-based rewriting scheme (CAP). The experimental results show that compared to HAR and CAP, CMR reduces the restoring time by 27.2% and 29.3%, respectively. Moreover, the deduplication ratio is improved by 1.91% and 4.36%, respectively. © 2

关键词： Metadata

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：