检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wu, Xiao-Ming Zheng, Dian Liu, Zuhao Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Binarization of neural networks is a dominant paradigm in neural networks compression. The pioneering work BinaryConnect uses Straight Through Estimator (STE) to mimic the gradients of the sign function, but it also causes the crucial inconsistency problem. Most of the previous methods design different estimators instead of STE to mitigate it. However, they ignore the fact that when reducing the estimating error, the gradient stability will decrease concomitantly. These highly divergent gradients will harm the model training and increase the risk of gradient vanishing and gradient exploding. To fully take the gradient stability into consideration, we present a new perspective to the BNNs training, regarding it as the equilibrium between the estimating error and the gradient stability. In this view, we firstly design two indicators to quantitatively demonstrate the equilibrium phenomenon. In addition, in order to balance the estimating error and the gradient stability well, we revise the original straight through estimator and propose a power function based estimator, Rectified Straight Through Estimator (ReSTE for short). Comparing to other estimators, ReSTE is rational and capable of flexibly balancing the estimating error with the gradient stability. Extensive experiments on CIFAR-10 and ImageNet datasets show that ReSTE has excellent performance and surpasses the state-of-the-art methods without any auxiliary modules or losses. Copyright © 2023, The Authors. All rights reserved.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Iterated Greedy Algorithm for the Distributed Flowshop Group Robust Scheduling Problem with Uncertain Processing Times

SSRN

引用

SSRN 2023年

作者： Wang, Zhi-Yuan Pan, Quan-Ke Gao, Liang Jing, Xue-Lei Sun, Qing School of Mechanical and Electrical Engineering and Automation Shanghai University Shanghai200444 China School of Computer Science Liaocheng University Liaocheng252000 China State Key Lab of Digital Manufacturing Equipment & Technology Huazhong University of Science & Technology Wuhan430074 China Network Information Center Liaocheng University Liaocheng252000 China

This paper studies a distributed flowshop group robust scheduling problem with uncertain processing times, which has great significance in actual production activities. A robust mathematical model and an efficacious cooperative iterated greedy (CIG) algorithm are proposed to address the studied problem. A heuristic method with a novel sequence rule is presented to obtain an initial solution. A dummy scenario method is developed to reduce the complexity of the multi-scenario environment and raise the convergence speed. Two iterated greedy processes are utilized to optimize the family scheduling sub-problem and the job scheduling sub-problem respectively. A cooperation mechanism is designed elaborately to emphasize the coupling relationship between sub-problems. A comparative and comprehensive evaluation is conducted by comparing CIG with six high-performing algorithms. The results indicate that CIG significantly outperforms the other competitors from the average relative deviation index. © 2023, The Authors. All rights reserved.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT ONLINE labEL CONSISTENT HASHING FOR LARGE-SCALE CROSS-MODAL RETRIEVAL

EFFICIENT ONLINE LABEL CONSISTENT HASHING FOR LARGE-SCALE CR...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Yi, Jinhan Liu, Xin Cheung, Yiu-Ming Xu, Xing Fan, Wentao He, Yi Department of Computer Science and Technology Huaqiao University Xiamen361021 China Xiamen Key Lab. of Computer Vision and Pattern Recognition Fujian Key Lab. of Big Data Intelligence and Security China Department of Computer Science Hong Kong Baptist University Kowloon Hong Kong School of Computer Science and Engineering University of Electronic Science and Technology of China China Provincial Key Laboratory for Computer Information Processing Technology Soochow University China

ISBN: (纸本)9781665438643

Existing cross-modal hashing still faces three challenges: (1) Most batch-based methods are unsuitable for processing large-scale and streaming data. (2) Current online methods often suffer from insufficient semantic association, while lacking flexibility to learn the hash functions for varying streaming data. (3) Existing supervised methods always require much computation time or accumulate large quantization loss to learn hash codes. To address above challenges, we present an efficient Online label Consistent Hashing (OLCH) for cross-modal retrieval, which aims to incrementally learn hash codes for the current arriving data, while updating the hash functions at a streaming manner. To be specific, an online semantic representation learning framework is designed to adaptively preserve the semantic similarity across different modalities, and a mini-batch online gradient descent approach associated with forward-backward splitting is developed to optimize the hash functions. Accordingly, the hash codes are adaptively learned online with the high discriminative capability, while avoiding high computation complexity to process the streaming data. Experimental results show its outstanding performance in comparison with the-state-of-arts. © 2021 IEEE Computer Society. All rights reserved.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Whole Process Simulation of VFTO Coupling to Power Transformer Core Earthing Conductor

Whole Process Simulation of VFTO Coupling to Power Transform...

引用

Sustainable Power and Energy Conference (iSPEC)

作者： Xuezhi Ke Zuo Yan Zhaohui Li Yang Peng Ma Xuejun Bailin Li School of Electrical and Electronic Information Engineering Hubei Polytechnic University Huangshi China Huazhong University of Science and Technology Wuhan China Hubei Key Lab. for Operation and Control of Cascade Hydropower Stations China Three Gorges University

During the field practice, it was found that, the Very Fast Transient Overvoltage (VFTO) intruding into transformer will couple the corresponding VFTO signal on core earthing conductor, which provides a new way to detect VFTO impulse. To demonstrate the feasibility of this new method, it is necessary to study the whole process of VFTO coupling to the core earthing conductor. Firstly, this paper establishes a time-varying parameter model of disconnector, and the generation and characteristics of VFTO are simulated. Then, referring to the existing high-frequency model of winding and combining with its structure, establishing the winding’s “parallel multi-conductor lossless transmission line and lumped parameter hybrid model” to simulate and analyze the propagation process of VFTO on the winding. Finally, according to the core structure and material parameters, establishing the high-frequency capacitance coupling model of the core, and uniting with the previous model to simulate and analyze the way of VFTO-pulse generated in Core Earthing Signals (CES). In addition, an actual case is modeled and simulated, the simulation results prove the correctness of simulation analysis and the feasibility of this new method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Structure and Route Algorithm for Hybrid DCN Network Based on ExCCC-DCN

A Novel Structure and Route Algorithm for Hybrid DCN Network...

引用

2020 International Conference on Internet of Things and Intelligent Applications, ITIA 2020

作者： Zhang, Yujie Han, Zhijie Song, Yunfei Nanjing University of Posts and Telecommunications School of Computer Science Nanjing China Henan University School of Computer and Information Engineering Kaifeng China System Engineering Institute Macau University of Science and Technology China

ISBN: (纸本)9781728193014

With the rapid development of data center network (DCN) technology, researchers have cleverly combined wireless connection and wired DCN to form a new structure, hybrid data center network (HDCN). Exchanged Cube-Connected Cycles (ExCCC) has high scalability and relatively low construction cost and operation energy consumption, which is very suitable for the deployment of large-scale data center. In this paper a novel hybrid ExCCC-DCN structure is proposed by combining the communication characteristics of 60GHz millimeter-wave technology. The transformed hybrid network not only inherits the original structural characteristics of ExCCC-DCN structure, but also effectively reduces the network data traffic and improves the network throughput. We divide the hybrid ExCCC-DCN into several units (pods), and propose a new cluster-based multicast routing algorithm. Comparative experiments prove that the algorithm can effectively reduce the number of multicast links and improve the data throughput during multicast communication when constructing a multicast tree. © 2020 IEEE.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

A high-performance and endurable SSD cache for parity-based RAID

引用

Frontiers of Computer science 2019年第1期13卷 16-34页

作者： Chu LI Dan FENG Yu HUA Fang WANG Wuhan National Lab for Optoelectronics Key Laboratory of Information Storage System(School of Computer Science and TechnologyHuazhong University of Science and Technology) Ministry of Education of ChinaWuhan 430074China

Solid-state drives (SSDs)have been widely used as caching tier for disk-based RAID systems to speed up dataintensive ***,traditional cache schemes fail to effectively boost the parity-based RAID storage sys- tems (e.g.,RAID-5/6),which have poor random write performance due to the small-write ***'s worse,intensive cache writes can wear out the SSD quickly,which causes performance degradation and cost *** this article,we present the design and implementation of KDD, an efficient SSD-based caching system which Keeps Data and Deltas in *** write requests hit in the cache, KDD dispatches the data to the RAID storage without updating the parity blocks to mitigate the small write penalty, and compactly stores the compressed deltas in SSD to reduce the cache write traffic while guaranteeing reliability in case of disk *** addition,KDD organizes the metadata partition on SSD as a circular log to make the cache persistent with low *** evaluate the performance of KDD via both simulations and prototype *** results show that KDD effectively reduces the small write penalty while extending the lifetime of the SSD-based cache by up to 6.85 times.

关键词： solid-state drive (SSD) parity-based RAID small write problem write endurance

来源：评论

学校读者我要写书评

暂无评论

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via...

引用

International Conference on Computer Vision (ICCV)

作者： Shenghao Fu Junkai Yan Yipeng Gao Xiaohua Xie Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Pengcheng Lab China

Recent sparse detectors with multiple, e.g. six, decoder layers achieve promising performance but much inference time due to complex heads. Previous works have explored using dense priors as initialization and built one-decoder-layer detectors. Although they gain remarkable acceleration, their performance still lags behind their six-decoder-layer counterparts by a large margin. In this work, we aim to bridge this performance gap while retaining fast speed. We find that the architecture discrepancy between dense and sparse detectors leads to feature conflict, hampering the performance of one-decoder-layer detectors. Thus we propose Adaptive Sparse Anchor Generator (ASAG) which predicts dynamic anchors on patches rather than grids in a sparse way so that it alleviates the feature conflict problem. For each image, ASAG dynamically selects which feature maps and which locations to predict, forming a fully adaptive way to generate image-specific anchors. Further, a simple and effective Query Weighting method eases the training instability from adaptiveness. Extensive experiments show that our method outperforms dense-initialized ones and achieves a better speed-accuracy trade-off. The code is available at https://***/iSEE-laboratory/ASAG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolution-enhanced Evolving Attention Networks

arXiv

引用

arXiv 2022年

作者： Wang, Yujing Yang, Yaming Li, Zhuo Bai, Jiangang Zhang, Mingliang Li, Xiangtai Yu, Jing Zhang, Ce Huang, Gao Tong, Yunhai Key Laboratory of Machine Perception MOE School of Intelligence Science and Technology Peking University China Department of Computer Science & Technology Engineering Research Center of Microprocessor & System Peking University China Institute of Information Engineering Chinese Academy of Sciences China ETH Zürich Switzerland The Department of Automation Tsinghua University China

Attention-based neural networks, such as Transformers, have become ubiquitous in numerous applications, including computer vision, natural language processing, and time-series analysis. In all kinds of attention networks, the attention maps are crucial as they encode semantic dependencies between input tokens. However, most existing attention networks perform modeling or reasoning based on representations, wherein the attention maps of different layers are learned separately without explicit interactions. In this paper, we propose a novel and generic evolving attention mechanism, which directly models the evolution of inter-token relationships through a chain of residual convolutional modules. The major motivations are twofold. On the one hand, the attention maps in different layers share transferable knowledge, thus adding a residual connection can facilitate the information flow of inter-token relationships across layers. On the other hand, there is naturally an evolutionary trend among attention maps at different abstraction levels, so it is beneficial to exploit a dedicated convolution-based module to capture this process. Equipped with the proposed mechanism, the convolution-enhanced evolving attention networks achieve superior performance in various applications, including time-series representation, natural language understanding, machine translation, and image classification. Especially on time-series representation tasks, Evolving Attention-enhanced Dilated Convolutional (EA-DC-) Transformer outperforms state-of-the-art models significantly, achieving an average of 17% improvement compared to the best SOTA. To the best of our knowledge, this is the first work that explicitly models the layer-wise evolution of attention maps. Our implementation is available at https://***/pkuyym/EvolvingAttention. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Mobile Phone Online Detection of Water Surface Evaporation of Evaporator and Intelligent Irrigation Control system Based on Pulse Counting Principle

SSRN

引用

SSRN 2023年

作者： Cao, Chunhao Yang, Qiliang Li, Jianian Yang, Ling Faculty of Modern Agricultural Engineering Kunming University of Science and Technology Kunming650500 China College of Mechanical and Electronic Engineering Northwest A&F University Shaanxi Yangling712100 China Yunnan Provincial Field Scientific Observation and Research Station on Water-Soil-Crop System in Seasonal Arid Region Kunming University of Science and Technology Kunming650500 China Yunnan Provincial Key Laboratory of High-efficiency Water Use and Green Production of Characteristic Crops in Universities Kunming University of Science and Technology Kunming650500 China Yunnan Technology Innovation Center of Phosphorus Resource Kunming650600 China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China

It is a time-consuming and laborious process to obtain the water surface evaporation of evaporator by traditional method to guide farmland irrigation. In addition, natural rainfall will seriously affect the detection of water surface evaporation, and the error caused by manual operation will also lead to the reduction of detection accuracy. To solve the above problems, an online water surface evaporation detection and remote control system based on the pulse counting principle is developed. The developed system includes the client subsystem, cloud subsystem, and detection and irrigation subsystem. The system realizes the functions of online accurate water surface evaporation, water filling, rainproofing, control irrigation, and so on. The Arduino Mega2560 and Arduino Uno development boards are adopted as the regular operation of the primary control core of the developed system. The water level is calculated by the number of pulses sent by the primary control core when the infrared water level probe moves from the initial position to the change of its level state after touching the water surface. GPRS Data Transfer Unit (DTU), as a data transmission module, establishes the communication between the cloud subsystem and the client subsystem;the micro-pump replenishes the evaporator, the rain sensor senses whether it rains, and the pulse water meter counts the irrigated water volume in real-time. The programmable Wi-Fi relay was used to control the hibernation of the circuit. The results showed that: 1) In the range of 10-70 mm water level, the number of pulses was highly linearly correlated with the water level, R2 = 1. 2) Compared with the traditional manual detection method, the relative error was between 0.59 and 1.80%. The operation of the device is stable and reliable, and the success rate of regular operation of the system was 100% after every operation. 3) Compared with the traditional method, this system saves operation time, simplifies operation steps, removes

关键词： Water levels

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Feedback Learning in Online Convex Games

arXiv

引用

arXiv 2023年

作者： Wang, Zifan Yi, Xinlei Shen, Yi Zavlanos, Michael M. Johansson, Karl H. Division of Decision and Control Systems School of Electrical Enginnering and Computer Science Kth Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden The Lab for Information & Decision Systems Massachusetts Institute of Technology United States The Department of Mechanical Engineering and Materials Science Duke University DurhamNC United States

This paper considers online convex games involving multiple agents that aim to minimize their own cost functions using locally available feedback. A common assumption in the study of such games is that the agents are symmetric, meaning that they have access to the same type of information or feedback. Here we lift this assumption, which is often violated in practice, and instead consider asymmetric agents;specifically, we assume some agents have access to first-order gradient feedback and others have access to the zeroth-order oracles (cost function evaluations). We propose an asymmetric feedback learning algorithm that combines the agent feedback mechanisms. We analyze the regret and Nash equilibrium convergence of this algorithm for convex games and strongly monotone games, respectively. Specifically, we show that our algorithm always performs between pure first-order and zeroth-order methods, and can match the performance of these two extremes by adjusting the number of agents with access to zeroth-order oracles. Therefore, our algorithm incorporates the pure first-order and zeroth-order methods as special cases. We provide numerical experiments on an online market problem for both deterministic and risk-averse games to demonstrate the performance of the proposed algorithm. Copyright © 2023, The Authors. All rights reserved.

关键词： Cost functions

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：