检索结果-内蒙古大学图书馆

Lay CO:Achieving Least Lossy Accuracy for Most Efficient RRAM-Based Deep Neural Network Accelerator via Layer-Centric Co-Optimization

引用

计算机科学技术学报（英文版） 2023年第2期38卷 328-347页

作者： Shao-Feng Zhao Fang Wang Bo Liu Dan Feng Yang Liu Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cloud Computing and Big Data Institute Henan University of Economics and LawZhengzhou 450001China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Research Institute of Huazhong University of Science and Technology in Shenzhen Shenzhen 518057China School of Computer and Artificial Intelligence Zhengzhou UniversityZhengzhou 450001China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cloud Computing and Big Data Institute Henan University of Economics and LawZhengzhou 450001China

Resistive random access memory(RRAM)enables the functionality of operating massively parallel dot prod-ucts and ***-based accelerator is such an effective approach to bridging the gap between Internet of Things devices'constrained resources and deep neural networks'tremendous *** to the huge overhead of Analog to Digital(A/D)and digital accumulations,analog RRAM buffer is introduced to extend the processing in analog and in *** analog RRAM buffer offers potential solutions to A/D conversion issues,the energy consumption is still challenging in resource-constrained environments,especially with enormous intermediate data ***,criti-cal concerns over endurance must also be resolved before the RRAM buffer could be frequently used in reality for DNN in-ference *** we propose LayCO,a layer-centric co-optimizing scheme to address the energy and endurance con-cerns altogether while strictly providing an inference accuracy *** relies on two key ideas:1)co-optimizing with reduced supply voltage and reduced bit-width of accelerator architectures to increase the DNN's error tolerance and achieve the accelerator's energy efficiency,and 2)efficiently mapping and swapping individual DNN data to a correspond-ing RRAM partition in a way that meets the endurance *** evaluation with representative DNN models demonstrates that LayCO outperforms the baseline RRAM buffer based accelerator by 27x improvement in energy effi-ciency(over TIMELY-like configuration),308x in lifetime prolongation and 6x in area reduction(over RAQ)while main-taining the DNN accuracy loss less than 1％.

关键词： deep learning accelerator resistive random access memory (RRAM) energy efficiency error tolerance

来源：评论

学校读者我要写书评

暂无评论

A multilayer network diffusion-based model for reviewer recommendation

引用

Chinese Physics B 2024年第3期33卷 700-717页

作者：黄羿炜徐舒琪蔡世民吕琳媛 Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengdu 611731China Yangtze Delta Region Institute (Huzhou) University of Electronic Science and Technology of ChinaHuzhou 313001China Institute of Dataspace Hefei Comprehensive National Science CenterHefei 230088China Big Data Research Center University of Electronic Science and Technology of ChinaChengdu 611731China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Cyber Science and Technology University of Science and Technology of ChinaHefei 230026China

With the rapid growth of manuscript submissions,finding eligible reviewers for every submission has become a heavy *** systems are powerful tools developed in computer science and information science to deal with this ***,most existing approaches resort to text mining techniques to match manuscripts with potential reviewers,which require high-quality textual information to perform *** this paper,we propose a reviewer recommendation algorithm based on a network diffusion process on a scholar-paper multilayer network,with no requirement for textual *** network incorporates the relationship of scholar-paper pairs,the collaboration among scholars,and the bibliographic coupling among *** results show that our proposed algorithm outperforms other state-of-the-art recommendation methods that use graph random walk and matrix factorization and methods that use machine learning and natural language processing,with improvements of over 7.62%in recall,5.66%in hit rate,and 47.53%in ranking *** work sheds light on the effectiveness of multilayer network diffusion-based methods in the reviewer recommendation problem,which will help to facilitate the peer-review process and promote information retrieval research in other practical scenes.

关键词： reviewer recommendation multilayer network network diffusion model recommender systems complex networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Relaxed Functional Dependency Discovery with Minimal Set Cover 40

Efficient Relaxed Functional Dependency Discovery with Minim...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Ding, Xiaoou Liu, Yida Wang, Hongzhi Wang, Chen Song, Yichen Yang, Donghua Wang, Jianmin School of Computer Science and Technology Harbin Institute of Technology China National Engineering Research Center for Big Data Software EIRI Tsinghua University China

ISBN: (纸本)9798350317152

Assessing data quality through Functional Depen-dencies (FDs) is a crucial aspect of data governance. However, with the diverse range of data sources and the exponential growth in data volume, exact FDs can sometimes be impractical for real-world applications. In contrast, relaxed functional dependencies (RFDs), which allows for some flexibility in attribute value comparisons, demonstrates greater adaptability and flexibility for big data scenarios. To address the efficient discovery of RFDs, this paper proposes a novel mining method to supplement the current research gaps. By establishing a difference table for tuples, we transform the problem into a specialized minimal set covering problem. Additionally, we introduce two optimization strategies: reducing the time complexity of enumerating the left-hand side of the base RFDs to 0 (1) and decreasing the search complexity for feasible LHS attributes and threshold candidates from O(2m-l) to O(1.5m-1). We rigorously proof that our mining approach guarantees the identification of validity and minimal RFDs. Experiments on nine real-world datasets reveal that our method significantly improves efficiency compared to existing techniques. Furthermore, it uncovers more concise and higher-quality RFDs. Importantly, the RFDs extracted through our methodology exhibit better performance in downstream cleaning tasks. © 2024 IEEE.

关键词： Quality management

来源：评论

学校读者我要写书评

暂无评论

SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow 38

SemFlow: Binding Semantic Segmentation and Image Synthesis v...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Chaoyang Li, Xiangtai Qi, Lu Ding, Henghui Tong, Yunhai Yang, Ming-Hsuan School of Intelligence Science and Technology Peking University China UC Merced United States Institute of Big Data Fudan University China

Semantic segmentation and semantic image synthesis are two representative tasks in visual perception and generation. While existing methods consider them as two distinct tasks, we propose a unified framework (SemFlow) and model them as a pair of reverse problems. Specifically, motivated by rectified flow theory, we train an ordinary differential equation (ODE) model to transport between the distributions of real images and semantic masks. As the training object is symmetric, samples belonging to the two distributions, images and semantic masks, can be effortlessly transferred reversibly. For semantic segmentation, our approach solves the contradiction between the randomness of diffusion outputs and the uniqueness of segmentation results. For image synthesis, we propose a finite perturbation approach to enhance the diversity of generated results without changing the semantic categories. Experiments show that our SemFlow achieves competitive results on semantic segmentation and semantic image synthesis tasks. We hope this simple framework will motivate people to rethink the unification of low-level and high-level vision. © 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

AMHF-TP:Multifunctional therapeutic peptides prediction based on multi-granularity hierarchical features

引用

Quantitative Biology 2025年第1期13卷 127-141页

作者： Shouheng Tuo YanLing Zhu Jiangkun Lin Jiewei Jiang School of Computer Science and Technology Xi’an University of Posts and TelecommunicationsXi’anChina Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’anChina Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’anChina School of Electronic Engineering Xi’an University of Posts and TelecommunicationsXi’anChina

Multifunctional therapeutic peptides(MFTP)hold immense potential in diverse therapeutic contexts,yet their prediction and identification remain challenging due to the limitations of traditional methodologies,such as extensive training durations,limited sample sizes,and inadequate generalization *** address these issues,we present AMHF-TP,an advanced method for MFTP recognition that utilizes attention mechanisms and multi-granularity hierarchical features to enhance *** AMHF-TP is composed of four key components:a migration learning module that leverages pretrained models to extract atomic compositional features of MFTP sequences;a convolutional neural network and selfattention module that refine feature extraction from amino acid sequences and their secondary structures;a hypergraph module that constructs a hypergraph for complex similarity representation between MFTP sequences;and a hierarchical feature extraction module that integrates multimodal peptide sequence *** with leading methods,the proposed AMHF-TP demonstrates superior precision,accuracy,and coverage,underscoring its effectiveness and robustness in MFTP *** comparative analysis of separate hierarchical models and the combined model,as well as with five contemporary models,reveals AMHFTP’s exceptional performance and stability in recognition tasks.

关键词： deep learning hypergraph multifunctional therapeutic peptides multi-granularity hierarchical features

来源：评论

学校读者我要写书评

暂无评论

A Diversion Path Planning Method of Waypoint Based on Flight Traffic Conduction 6

A Diversion Path Planning Method of Waypoint Based on Flight...

引用

6th IEEE International Conference on Civil Aviation Safety and Information technology, ICCASIT 2024

作者： Shi, Hongfang Le, Ningning Miao, Jiahe Li, Qian China Academy of Civil Aviation Science and Technology Big Data Analysis and Application Center Beijing China

ISBN: (纸本)9798350389418

Based on flight operation data, this paper constructs a diversion path planning method for busy waypoints by analyzing the relationship of flight traffic conduction between waypoints. Taking busy waypoint KHN as an example, a total of two diversion paths are planned, specifically one in the east-west direction and one in the north-south direction, and the two diversion paths are evaluated in terms of safety and economy, and the results of the evaluations are within the acceptable range. The method of this paper can improve the capacity of airspace resources without changing the existing air route network;at the same time, this method can also assist in identifying the bottleneck of airspace resources, which means identifying the key waypoints affecting the flow of diversion paths, so as to provide certain theoretical references for China to enhance the total number of flights, and to improve the utilization rate of airspace resources and operational efficiency. © 2024 IEEE.

关键词： Flight paths

来源：评论

学校读者我要写书评

暂无评论

A Multi-layer data Encryption Method Based on Reverse Artificial Swarm Algorithm and Packet Convolutional Chaotic Sequence

引用

International Journal of Network Security 2024年第3期26卷 417-424页

作者： Du, Yuankun Liu, Fengping Wang, Fei School of Big Data and Artificial Intelligence Zhengzhou University of Science and Technology Zhengzhou450064 China School of Information Engineering Zhengzhou University of Science and Technology Zhengzhou450064 China School of Information Engineering Henan Institute of Animal Husbandry Economics Zhengzhou450064 China

In order to improve the security of data and reduce the risk of data being modified and stolen during transmission and storage, a multi-layer data encryption method based on reverse artificial swarm algorithm and packet convolutional chaotic sequence is proposed. Firstly, residual and grouped convolution blocks extract and utilize image features. Secondly, in order to avoid falling into the local optimal, the reverse learning strategy is introduced in the three stages of population initialization, hiring bees, and observing bees, respectively. The reverse order strategy between two points and the element exchange strategy is adopted to accelerate the optimization speed. According to the chaotic Frank sequence, the data is encrypted by multiple layers. The experimental results show that the proposed method has a high scrambling performance. The time required for ciphertext generation is less than 100ms, the encryption efficiency is high, and the data security is improved. © (2024), (International Journal of Network Security). All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

The symmetric space,strong isotropy irreducibility and equigeodesic properties

引用

science China Mathematics 2024年第1期67卷 129-148页

作者： Ming Xu Ju Tan School of Mathematical Sciences Capital Normal UniversityBeijing 100048China School of Microelectronics and Data Science Anhui University of TechnologyMa'anshan 243032China

A smooth curve on a homogeneous manifold G/H is called a Riemannian equigeodesic if it is a homogeneous geodesic for any G-invariant Riemannian *** homogeneous manifold G/H is called Riemannian equigeodesic,if for any x∈G/H and any nonzero y∈Tx(G/H),there exists a Riemannian equigeodesic c(t) with c(0)=x and ■(0)=*** two notions can be naturally transferred to the Finsler setting,which provides the definitions for Finsler equigeodesics and Finsler equigeodesic *** prove two classification theorems for Riemannian equigeodesic spaces and Finsler equigeodesic spaces,***,a homogeneous manifold G/H with a connected simply connected quasi compact G and a connected H is Riemannian equigeodesic if and only if it can be decomposed as a product of Euclidean factors and compact strongly isotropy irreducible ***,a homogeneous manifold G/H with a compact semisimple G is Finsler equigeodesic if and only if it can be locally decomposed as a product,in which each factor is Spin(7)/G2,G2/SU (3) or a symmetric space of compact *** results imply that the symmetric space and the strongly isotropy irreducible space of compact type can be interpreted by equigeodesic *** an application,we classify the homogeneous manifold G/H with a compact semisimple G such that all the G-invariant Finsler metrics on G/H are *** suggests a new project in homogeneous Finsler geometry,i.e.,to systematically study the homogeneous manifold G/H on which all the G-invariant Finsler metrics satisfy a certain geometric property.

关键词： equigeodesic equigeodesic space flag manifold orbit type stratification symmetric space strongly isotropy irreducible space

来源：评论

学校读者我要写书评

暂无评论

TSDDISCOVER: Discovering data Dependency for Time Series data 40

TSDDISCOVER: Discovering Data Dependency for Time Series Dat...

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Ding, Xiaoou Li, Yingze Wang, Hongzhi Wang, Chen Liu, Yida Wang, Jianmin School of Computer Science and Technology Harbin Institute of Technology China Tsinghua University National Engineering Research Center for Big Data Software EIRI China

ISBN: (纸本)9798350317152

Intelligent devices often produce time series data that suffer from significant data quality issues. While the utilization of data dependency in error detection and data repair has been somewhat beneficial, it remains inadequate in accurately representing the data quality of time series datasets. In recognition of the obvious characteristics inherent in time series data, we introduce a novel data dependency, termed TSDD. It effectively captures the contextual relationships embedded within multivariate time series, thereby enhancing the semantic richness of data quality representations. We analyze the complexity of both implication and consistency problems for TSDD reasoning, and develop TSDD discovery algorithm TSDDISCOVER, which consists of functional structure discovery, allowable error bound determination, and validation of TSDD patterns. Experimental results on real-life datasets verify TSDDISCOVER efficiently discovers high-quality TSDD patterns. In comparing the performance of TSDD-based error detection with several leading data quality constraints, our findings reveal that the former achieves an average improvement of 12% in accuracy and 30% in the F1 score over other dependency-based detection methods. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

From Segmentation to Generation: the Emerging Trends in Skin Lesion Detection 8

From Segmentation to Generation: the Emerging Trends in Skin...

引用

8th International Symposium on Computer science and Intelligent Control, ISCSIC 2024

作者： Yu, Junwei Xia, Yuhe Henan University of Technology School of Artificial Intelligence and Big Data Zhengzhou China Henan University of Technology College of Information Science and Engineering Zhengzhou China

ISBN: (纸本)9798350380286

Skin disease detection has undergone significant advancements with the advent of deep learning-based image segmentation techniques. In this paper, we provide a comprehensive overview of the evolution of skin disease detection, from traditional methods to modernapproaches. We discuss the role of U-Net and its variants in medical image segmentation, highlighting their improved performance and robustness through multi-scale features, multi-task learning, and attention mechanisms. Additionally, we explore the recent trend of generation-based methods, including generative adversarial networks and diffusion models, which have shown promising results in generating high-quality skin disease segmentation masks. We also review popular skin disease segmentation datasets and evaluation metrics,and present experimental results comparing the performance of various models. As deep learning continues to advance and skin disease datasets expand, we anticipate the emergence of innovative network architectures and technologies that will further improve the diagnosis and treatment of skin diseases. This paper aims to inspire future research in this direction, exploring the potential of generation-based methods for skin disease detection and paving the way for more accurate and efficient diagnosis and treatment. © 2024 IEEE.

关键词： Generative adversarial networks

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：