检索结果-内蒙古大学图书馆

IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Heng Zhou Bing Wu Huan Cheng Jinpeng Liu Taoming Lei Dan Feng Wei Tong Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology School of Computer Science and Technology Huazhong University of Science and Technology Ministry of Education of China

ISBN: (数字)9798350350579

ISBN: (纸本)9798350350586

The memristive Computing-in-Memory (CIM) sys-tem can efficiently accelerate matrix-vector multiplication (MVM) operations through in-situ computing. The data layout has a significant impact on the communication performance of CIM systems. Existing software-level communication opti-mizations aim to reduce communication distance by carefully designing static data layouts, while wear-leveling (WL) and error mitigation methods use dynamic scheduling to enhance system reliability, resulting in randomized data layouts and increased communication overhead. Besides, existing CIM compilers di-rectly map data to physical crossbars and generate instructions, which causes inconvenience for dynamic scheduling. To address these challenges of balancing communication performance and reliability while coordinating existing CIM compilers and dy-namic scheduling, we propose a disorder-resistant computation translation layer (DRCTL), which improves system lifetime and communication performance through co-optimization of data layout and dynamic scheduling. It consists of three parts: (1) We propose an address conversion method for dynamic scheduling, which updates the addresses in the instruction stream after dynamic scheduling, thereby avoiding recompilation. (2) Dynamic scheduling strategy for reliability improvement. We propose a hierarchical wear-leveling (HWL) strategy, which reduces communication by increasing scheduling granularity. (3) Communication optimization for dynamic scheduling. We propose data layout-aware selective remapping (LASR), which helps dynamic scheduling methods improve communication lo-cality and reduce latency by exploiting data dependencies. The experiments demonstrate that HWL extends lifetime by 100.3-205.9 x compared to not using WL. Even with a slight lifetime decrease compared to the state-of-the-art WL (TIWL), it still supports continuous neural network training for 7 years. After applying LASR to HWL, the number of execution cycles, energy consumption

关键词： Training Energy consumption Processor scheduling Layout Dynamic scheduling In-memory computing Common Information Model (computing) System-on-chip Reliability Optimization

来源：评论

学校读者我要写书评

暂无评论

Quantum-Inspired Distributed Memetic Algorithm

引用

complex System Modeling and Simulation 2022年第4期2卷 334-353页

作者： Guanghui Zhang Wenjing Ma keyi Xing Lining Xing Kesheng Wang the School of Information Science and Technology and the Hebei Key Laboratory of Agricultural Big Data Hebei Agricultural UniversityBaoding 071001China the School of Information Science and Technology Hebei Agricultural UniversityBaoding 071001China. the State Key Laboratory for Manufacturing System Engineering and the Systems Engineering Institute Xi’an Jiaotong UniversityXi’an 710049China the School of Electronic Xidian UniversityXi’an 710071China the Department of Production and Quality Engineering Norwegian University of Science and TechnologyTrondheim 7491Norway

This paper proposed a novel distributed memetic evolutionary model,where four modules distributed exploration,intensified exploitation,knowledge transfer,and evolutionary restart are coevolved to maximize their strengths and achieve superior global *** exploration evolves three independent populations by heterogenous *** exploitation evolves an external elite archive in parallel with exploration to balance global and local *** transfer is based on a point-ring communication topology to share successful experiences among distinct search *** restart adopts an adaptive perturbation strategy to control search diversity *** computation is a newly emerging technique,which has powerful computing power and parallelized ***,this paper further fuses quantum mechanisms into the proposed evolutionary model to build a new evolutionary algorithm,referred to as quantum-inspired distributed memetic algorithm(QDMA).In QDMA,individuals are represented by the quantum characteristics and evolved by the quantum-inspired evolutionary optimizers in the quantum *** QDMA integrates the superiorities of distributed,memetic,and quantum *** experiments are carried out to evaluate the superior performance of *** results demonstrate the effectiveness of special designs and show that QDMA has greater superiority compared to the compared state-of-the-art algorithms based on Wilcoxon’s rank-sum *** superiority is attributed not only to good cooperative coevolution of distributed memetic evolutionary model,but also to superior designs of each special component.

关键词： distributed evolutionary algorithm memetic algorithm quantum-inspired evolutionary algorithm quantum distributed memetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Multilingual Lexical Simplification via Zero-Shot Paraphrasing

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2200-2214页

作者： Kang Liu Jipeng Qiang Yun Li Yi Zhu Yunhao Yuan Kaixun Hua Xindong Wu Department of Computer Science Yangzhou University Yangzhou China Department of Industrial and Management Systems Engineering University of South Florida Tampa USA Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei China

Lexical simplification (LS) method based on pretrained language models is a straightforward yet powerful approach for generating potential substitutes for a complex word through analysis of its contextual surroundings. Nonetheless, these methods necessitate distinct pretrained models tailored to diverse languages, often overlooking the imperative task of preserving a sentence’s meaning. In this paper, we propose a novel multilingual LS method via zero-shot paraphrasing (LSPG), as paraphrases provide diversity in word selection while preserving the sentence’s meaning. We regard paraphrasing as a zero-shot translation task within multilingual neural machine translation that supports hundreds of languages. Once the input sentence is channeled into the paraphrasing, we embark on the generation of the substitutes. This endeavor is underpinned by a pioneering decoding strategy that concentrates exclusively on the lexical modifications of the complex word. To utilize the strong capabilities of large language models (LLM), we further introduce a novel approach PromLS that incorporates the results of LSPG to generate heuristic-enhanced context, enabling the LLM to generate diverse candidate substitutions. Experimental results demonstrate that LSPG surpasses BERT-based methods and zero-shot GPT3-based methods significantly in English, Spanish, and Portuguese. We also demonstrate a substantial improvement achieved by PromLS compared to the previous state-of-the-art LLM approach. LS approaches usually assume that complex words and their replacements are individual terms, concentrating on word-for-word substitutions. To tackle the more challenging task of multi-word lexical simplification, including phrase-to-phrase replacements, we extend LSPG and PromLS into MultiLSPG and MultiPromLS. MultiLSPG identifies multi-word expressions matched with their corresponding word counts in specific positions, while MultiPromLS, akin to PromLS, utilizes these candidates to generate a heuristi

关键词： Multilingual Decoding Translation Rhetoric Large language models Training Neural machine translation Encoding Speech processing Probability distribution

来源：评论

学校读者我要写书评

暂无评论

Deconvolutional artificial-neural-network framework for subfilter-scale models of compressible turbulence

引用

Acta Mechanica Sinica 2021年第12期37卷 1773-1785页

作者： Zelong Yuan Yunpeng Wang Chenyue Xie Jianchun Wang Guangdong Provincial Key Laboratory of Foundemental Turbulence Research and Applications Center for Complex Flows and Soft Matter ResearchDepartment of Mechanics and Aerospace EngineeringSouthern University of Science and TechnologyShenzhen 518055China Guangdong-Hong Kong-Macao Joint Laboratory for Data-Driven Fluid Mechanics and Engineering Applications Southern University of Science and TechnologyShenzhen 518055China

We establish a deconvolutional artificial-neural-network(D-ANN)approach in large-eddy simulation(LES)of compressible turbulent *** variables in the neighboring locations are taken as the inputs of D-ANN to recover original(unfiltered)variables,including density,momentum and *** scale-similarity form is adopted to reconstruct subfilter-scale(SFS)*** proposed D-ANN models can give better a priori predictions of the sub-filter stress and heat flux than the classical approximate-deconvolution method(ADM)and the velocity-gradient model(VGM).The predicted SFS terms with the D-ANN models have correlation coefficients larger than 98.4%and relative errors smaller than 18%.In the a posteriori analysis,the D-ANN model compares against the implicit LES(ILES),the dynamic-Smagorinsky model(DSM),and the dynamic-mixed model(DMM).The D-ANN model predicts better than these classical models for velocity spectra,statistical properties of SFS kinetic energy flux and velocity *** turbulence statistics and transient velocity divergence are also accurately *** type of explicit filter and the impact of compressibility do not significantly affect a posteriori accuracy of the D-ANN *** showthat the proposed D-ANN approach has a great potential in developing highly accurate SFS models for large-eddy simulation of complex compressible turbulent flow.

关键词： Subfilter-scale model Large-eddy simulation Artificial neural network Machine learning Compressible turbulence

来源：评论

学校读者我要写书评

暂无评论

CorcPUM: Efficient Processing Using Cross-Point Memory via Cooperative Row-Column Access Pipelining and Adaptive Timing Optimization in Subarrays 23

CorcPUM: Efficient Processing Using Cross-Point Memory via C...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Chengning Wang Dan Feng Wei Tong Jingning Liu Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China (School of Computer Science and Technology Huazhong University of Science and Technology) Wuhan China

ISBN: (纸本)9798350323481

Emerging cross-point memory can in-situ perform vector-matrix multiplication (VMM) for energy-efficient scientific computation. However, parasitic-capacitance-induced row charging and discharging latency is a major performance bottleneck of subarray VMM. We propose a memory-timing-compliant bulk VMM processing-using-memory design with row access and column access co-optimization from rethinking of read access commands and μ-op timing. We propose row-level-parallelism-adaptive timing termination mechanism to reduce tail latency of tRCD and tRP by exploiting row nonlinear charging and bulk-interleaved row-column-cooperative VMM access mechanism to reduce tRAS and overlap CL without increasing column ADC precision. Evaluations show that our design can achieve 5.03× performance speedup compared with an aggressive baseline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Quality Evaluation of Academic Papers in Carbon Capture, Utilization, and Storage

The Quality Evaluation of Academic Papers in Carbon Capture,...

引用

2022 International Conference on Machine Learning, Control, and Robotics, MLCR 2022

作者： Zhang, Hangyue Bai, Jie School of Computer Science and Technology Sun Yat-sen University Guangzhou510275 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China

ISBN: (纸本)9781665454599

Carbon capture, utilization, and storage (CCUS) technology is a research hotspot worldwide owing to global climate change and warm gas control. CCUS papers from the last twenty years, derived from the Web of science database, were analyzed to investigate the impact and citation of academic papers using machine learning methods. Firstly, nine author characteristics, keywords, and three other categories were extracted from the literature. Then, the natural logarithm distribution of the annual average number of citations was obtained, and five evaluation grades were decided based on the citations. Next, the keyword evolution of papers in the CCUS field is analyzed, and a model on the keyword evolution trend index is proposed. data integration and imbalance processing were conducted after random sampling. A citation prediction model was proposed to evaluate the quality of CCUS academic papers and was verified on the recent five years' CCUS papers by comparing it with nine other mainstream machine learning models. The results indicate that the random forest model exhibits the best performance, with an accuracy rate reaching 88.7%;an ablation experiment was also conducted using the same algorithm. The results prove the effectiveness of our proposed method, shedding light on the quality of academic papers and technology development in CCUS. © 2022 IEEE.

关键词： Climate change

来源：评论

学校读者我要写书评

暂无评论

Steps Toward Industry 5.0:Building“6S”Parallel Industries With Cyber-Physical-Social Intelligence

引用

IEEE/CAA Journal of Automatica Sinica 2023年第8期10卷 1692-1703页

作者： Xingxia Wang Jing Yang Yutong Wang Qinghai Miao Fei-Yue Wang Aijun Zhao Jian-Ling Deng Lingxi Li Xiaoxiang Na Ljubo Vlacic School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China IEEE Macao University of Science and Technology Macao 999078China Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of SciencesBeijing 100098 State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China North Automatic Control Technology Institute Taiyuan 030006China China Huaneng Group Co. Ltd.Beijing 100031China Department of Electrical and Computer Engineering Indiana University-Purdue University Indianapolis(IUPUI)IndianapolisIN 46202 USA Department of Engineering University of CambridgeCambridgeCB21PZUK School of Engineering and Built Environment Griffith UniversityGold CoastQLD 4222Australia

Very recently,intensive discussions and studies on Industry 5.0 have sprung up and caused the attention of researchers,entrepreneurs,and policymakers from various sectors around the ***,there is no consensus on why and what is Industry 5.0 *** this paper,we define Industry 5.0from its philosophical and historical origin and evolution,emphasize its new thinking on virtual-real duality and human-machine interaction,and introduce its new theory and technology based on parallel intelligence(PI),artificial societies,computational experiments,and parallel execution(the ACP method),and cyber-physical-social systems(CPSS).Case studies and applications of Industry 5.0 over the last decade have been briefly summarized and analyzed with suggestions for its future *** believe that Industry 5.0 of virtual-real interactive parallel industries has great potentials and is critical for building smart *** are outlined to ensure a roadmap that would lead to a smooth transition from CPS-based Industry 4.0 to CPSS-based Industry 5.0 for a better world which is Safe in physical spaces,S ecure in cyberspaces,Sustainable in ecology,Sensitive in individual privacy and rights,Service for all,and Smartness of all.

关键词： ACP artificial intelligence CPS CPSS Industry 4.0 Industry 5.0 parallel industries parallel intelligence

来源：评论

学校读者我要写书评

暂无评论

In-situ preparation of Cu-BTC modified with organic amines for H_(2)S removal under ambient conditions

引用

Resources Chemicals and Materials 2023年第2期2卷 143-150页

作者： Zhelin Su Mingxian Duan Yeshuang Wang Huiling Fan Zhen Tian Zhaohui Chen Chao Yang Ju Shangguan State Key Laboratory of Clean and Efficient Coal Utilization Co-founded by Shanxi Province and the Ministry of Science and TechnologyTaiyuan University of TechnologyWest Yingze Street Number 79Taiyuan030024China School of Resources and Environmental Engineering Shanghai Polytechnic UniversityShanghai 201209China State Key Laboratory of Multi-phase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing 100190China College of Environmental Science and Engineering Taiyuan University of TechnologyTaiyuan 030024China

Amine modification is an effective strategy to improve the H_(2)S removal performance of *** order to avoid the problem of pore blockage after amine modification in post synthesis impregnation,herein a series of Cu-BTC modified with organic amine adsorbents were prepared via an in-situ one-pot method and the H_(2)S removal performance under ambient conditions was *** is found that the introduced organic amines,depending on the types of amine selected,have a significant influence on the growth of Cu-BTC and its textural *** H_(2)S removal performance on the as-prepared materials suggested that the amine modified samples remarkably improved the H_(2)S removal capacities with an order of BA-Cu-BTC>TEA-Cu-BTC>TEOA-Cu-BTC>*** the enlarged surface area and the increased mesopores volumes,BA has the advantages of smaller steric hindrance and-NH_(2)groups,among which the former increased the accessibility of Cu active sites while the latter acted as additional active sites for H_(2)S capturing,thus affording BA-Cu-BTC highest breakthrough capacity of 77.3 mg S/***,this study elaborates the effect of organic amines in-situ modification on the Cu-BTC structure and desulfurization.

关键词： In-situ preparation Organic amines Cu-BTC H_(2)S adsorption

来源：评论

学校读者我要写书评

暂无评论

BMP-SD: Marrying Binary and Mixed-Precision Quantization for Efficient Stable Diffusion Inference

BMP-SD: Marrying Binary and Mixed-Precision Quantization for...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Cheng Gu Gang Li Xiaolong Lin Jiayao Ling Jian Cheng Xiaoyao Liang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China The Key Laboratory of Cognition and Decision Intelligence for Complex Systems CASIA Beijing China AiRiA Nanjing China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

Stable Diffusion (SD) is an emerging deep neural network (DNN) model that has demonstrated impressive capabilities in generative tasks such as text-to-image generation. However, the iterative denoising stage of the SD model is extremely expensive in both computations and memory accesses, making it challenging for fast and energy-efficient edge deployment. To alleviate the overhead of denoising, in this paper we propose BMP-SD, a post-training quantization framework for hardware-efficient SD inference. BMP-SD employs binary weight quantization to significantly reduce the computational complexity and memory footprint of iterative denoising, along with dynamic step-aware mixed-precision activation quantization, based on the observation that not all denoising steps are equally important for a specific input prompt. Experiments on the text-to-image generation task show that BMP-SD achieves mixed-precision (W1.73A4.87) with minimal accuracy loss on MS-COCO 2014 dataset. We also evaluate the BMP-SD quantized model on three state-of-the-art bit-flexible DNN accelerators, results reveal that our method can deliver up to 5.14× performance and 3.85×energy efficiency improvements compared to W8A8 quantization.

关键词： Quantization (signal) Accuracy Computational modeling Noise reduction Text to image Europe Artificial neural networks Energy efficiency Iterative methods Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Large Language Models are Few-Shot Summarizers: Multi-Intent Comment Generation via In-Context Learning

Large Language Models are Few-Shot Summarizers: Multi-Intent...

引用

International Conference on Software Engineering (ICSE)

作者： Mingyang Geng Shangwen Wang Dezun Dong Haotian Wang Ge Li Zhi Jin Xiaoguang Mao Xiangke Liao College of Computer Science National University of Defense Technology Changsha China Key Laboratory of Software Engineering for Complex Systems Key Lab of High Confidence Software Technology Peking University Beijing China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Code comment generation aims at generating natural language descriptions for a code snippet to facilitate developers' program comprehension activities. Despite being studied for a long time, a bottleneck for existing approaches is that given a code snippet, they can only generate one comment while developers usually need to know information from diverse perspectives such as what is the functionality of this code snippet and how to use it. To tackle this limitation, this study empirically investigates the feasibility of utilizing large language models (LLMs) to generate comments that can fulfill developers' diverse intents. Our intuition is based on the facts that (1) the code and its pairwise comment are used during the pre-training process of LLMs to build the semantic connection between the natural language and programming language, and (2) comments in the real-world projects, which are collected for the pre-training, usually contain different developers' intents. We thus postulate that the LLMs can already understand the code from different perspectives after the pre-training. Indeed, experiments on two large-scale datasets demonstrate the rationale of our insights: by adopting the in-context learning paradigm and giving adequate prompts to the LLM (e.g., providing it with ten or more examples), the LLM can significantly outperform a state-of-the-art supervised learning approach on generating comments with multiple intents. Results also show that customized strategies for constructing the prompts and post-processing strategies for reranking the results can both boost the LLM's performances, which shed light on future research directions for using LLMs to achieve comment generation.

关键词： Computer languages Codes Supervised learning Natural languages Semantics Task analysis Software engineering

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：