检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Hongyu Liu Runmin Cong Hua Li Qianqian Xu Qingming Huang Wei Zhang Institute of Information Science Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University & Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal scheduling of single-arm multi-cluster tools with two-space buffering modules

Optimal scheduling of single-arm multi-cluster tools with tw...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： FaJun Yang NaiQi Wu Yan Qiao MengChu Zhou Department of Industrial Engineering Guangdong University of Technology Guangzhou China Institute of Systems Engineering Macau University of Science and Technology Macau Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

A multi-cluster tool is composed of a number of single-cluster tools linked by buffering modules. The capacity of a buffering module can be one or two. Aiming at finding an optimal one-wafer cyclic schedule, this work explores the effect of two-space buffering modules on the performance of a multi-cluster tool. The tool is modeled by a kind of Petri nets. The dynamic behavior of robot waiting and tasks, process modules, and buffers is well captured by the net model. With the model, this work shows that there is always a one-wafer cyclic schedule that reaches the lower bound of the cycle time of a process-dominant tool. Furthermore, a constant-time algorithm is revealed to find such a schedule for the first time for such multi-cluster tools. An illustrative example is given to show the application and power of this new method.

关键词： Schedules Robot kinematics Firing Semiconductor device modeling Fires Load modeling

来源：评论

学校读者我要写书评

暂无评论

On Theoretical Optimization of the Sensing Matrix for Sparse-Dictionary Signal Recovery

On Theoretical Optimization of the Sensing Matrix for Sparse...

引用

IEEE Global Conference on Signal and Information Processing (GlobalSIP)

作者： Jianchen Zhu Shengjie Zhao Xu Ma Gonzalo R. Arce Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai CHN School of Optics and Photonics Beijing Institute of Technology Beijing CHN Department of Electrical and Computer Engineering University of Delaware Newark Delaware USA

Compressive Sensing (CS) is a new paradigm for the efficient acquisition of signals that have sparse representation in a certain domain. Traditionally, CS has provided numerous methods for signal recovery over an orthonormal basis. However, modern applications have sparked the emergence of related methods for signals not sparse in an orthonormal basis but in some arbitrary, perhaps highly overcomplete, dictionary, particularly due to their potential to generate different kinds of sparse representation of signals. Here, we first propose the Signal space Subspace Pursuit (SSSP) algorithm, and then we derive a low bound on the number of measurements required. The algorithm has low computational complexity and provides high recovery accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Realizing Emotional Interactions to Learn User Experience and Guide Energy Optimization for Mobile architectures 22

Realizing Emotional Interactions to Learn User Experience an...

引用

Proceedings of the 55th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Xueliang Li Zhuobin Shi Junyang Chen Yepang Liu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation and Department of Computer Science and Engineering Southern University of Science and Technology China

ISBN: (纸本)9781665462723

In the age of AI, mobile architectures such as smartphones are still "cold machines"; machines do not feel. If the architecture is able to feel users' feelings and runtime user experience (UX), it will accordingly adapt performance/energy to find the optimal system-operating state that consumes the least energy to satisfy users. In this paper, we will utilize users' facial expressions (FEs) to learn their runtime UX. We know that FEs are the natural and direct way for humans to convey their emotions and feelings. Our study reveals that FEs also reflect UX. Our research for the first time quantifies the link between FEs and UX. Leveraging this link, the architecture will be able to use the front camera to see FEs and feel users' UX. Based on UX, the architecture can appropriately provision computing resources. We propose Vi-energy system to realize the above idea. Our evaluation shows that Vi-energy reduces energy consumption by 52.9% at maximum and secures UX.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

International Journal on Artificial Intelligence Tools 2012年第3期21卷 1202003-1202003页

作者： Cui, Zhihua Shi, Zhongzhi Alex, Rajan Complex System and Computational Intelligence Laboratory School of Computer Science and Technology Taiyuan University of Science and Technology Shanxi 030024 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences No. 6 Kexueyuan South Road Zhongguancun Haidian District Beijing 100190 China Department of Engineering and Computer Science West Texas AandM University Canyon TX 79015 United States

Swarm intelligence is an umbrella for amount optimization algorithms. This discipline deals with natural and artificial systems composed of many individuals that coordinate their activities using decentralized control and self-organization. In general, multi-agent systems that use some swarm intelligence are said to be swarm intelligent systems. They are mostly used as search engines and optimization tools. The goal of this special issue has been to offer a wide spectrum of sample works throughout the world about innovative methodologies of swarm intelligence. The issue should be useful both for beginners and experienced researchers in the field of computational intelligence. © 2012 World Scientific Publishing Company.

关键词： Swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

FTT-NAS: Discovering fault-tolerant convolutional neural architecture

arXiv

引用

arXiv 2020年

作者： Ning, Xuefei Ge, Guangjun Li, Wenshuo Zhu, Zhenhua Zheng, Yin Chen, Xiaoming Gao, Zhen Wang, Yu Yang, Huazhong Department of Electronic Engineering Tsinghua University China Weixin Group Tencent China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China School of Electrical and Information Engineering Tianjin University China

With the fast evolvement of embedded deep-learning computing systems, applications powered by deep learning are moving from the cloud to the edge. When deploying neural networks (NNs) onto the devices under complex environments, there are various types of possible faults: soft errors caused by cosmic radiation and radioactive impurities, voltage instability, aging, temperature variations, malicious attackers, etc. Thus the safety risk of deploying NNs is now drawing much attention. In this paper, after the analysis of the possible faults in various types of NN accelerators, we formalize and implement various fault models from the algorithmic perspective. We propose Fault-Tolerant Neural architecture Search (FT-NAS) to automatically discover convolutional neural network (CNN) architectures that are reliable to various faults in nowadays devices. Then we incorporate fault-tolerant training (FTT) in the search process to achieve better results, which is referred to as FTT-NAS. Experiments on CIFAR-10 show that the discovered architectures outperform other manually designed baseline architectures significantly, with comparable or fewer floating-point operations (FLOPs) and parameters. Specifically, with the same fault settings, F-FTT-Net discovered under the feature fault model achieves an accuracy of 86.2% (VS. 68.1% achieved by MobileNet-V2), and W-FTT-Net discovered under the weight fault model achieves an accuracy of 69.6% (VS. 60.8% achieved by ResNet-18). By inspecting the discovered architectures, we find that the operation primitives, the weight quantization range, the capacity of the model, and the connection pattern have influences on the fault resilience capability of NN models. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Divide-and-conquer variational quantum algorithms for large-scale electronic structure simulations

arXiv

引用

arXiv 2022年

作者： Ma, Huan Fan, Yi Liu, Jie Shang, Honghui Li, Zhenyu Yang, Jinlong Hefei National Laboratory University of Science and Technology of China Hefei230088 China Hefei National Research Center for Physical Sciences at the Microscale University of Science and Technology of China Hefei230026 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

Exploring the potential application of quantum computers in material design and drug discovery has attracted a lot of interest in the age of quantum computing. However, the quantum resource requirement for solving practical electronic structure problems are far beyond the capacity of near-term quantum devices. In this work, we integrate the divide-and-conquer (DC) approaches into the variational quantum eigensolver (VQE) for large-scale quantum computational chemistry simulations. Two popular divide-and-conquer schemes, including many-body expansion (MBE) fragmentation theory and density matrix embedding theory (DMET), are employed to divide complicated problems into many small parts that are easy to implement on near-term quantum computers. Pilot applications of these methods to systems consisting of tens of atoms are performed with adaptive VQE algorithms. This work should encourage further studies of using the philosophy of DC to solve electronic structure problems on quantum computers. © 2022, CC BY.

关键词： Electronic structure

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Neural Network Based Preselection for Expensive Multi-Objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Li, Bingdong Yang, Yanting Hong, Wenjing Yang, Peng Zhou, Aimin Shanghai Institute of AI for Education the School of Computer Science and Technology and the Shanghai Frontiers Science Center of Molecule Intelligent Syntheses East China Normal University Shanghai China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science and Engineering Guangdong Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

A series of surrogate-assisted evolutionary algorithms (SAEAs) have been proposed for expensive multi-objective optimization problems (EMOPs), building cheap surrogate models to replace the expensive real function evaluations. However, the search efficiency of these SAEAs is not yet satisfactory. More efforts are needed to further exploit useful information from the real function evaluations in order to better guide the search process. Facing this challenge, this paper proposes a Hyperbolic Neural Network (HNN) based preselection operator to accelerate the optimization process based on limited evaluated solutions. First, the preselection task is modeled as a multi-label classification problem where solutions are classified into different layers (ordinal categories) through -relaxed objective aggregation. Second, in order to resemble the hierarchical structure of candidate solutions, a hyperbolic neural network is applied to tackle the multi-label classification problem. The reason for using HNN is that hyperbolic spaces more closely resemble hierarchical structures than Euclidean spaces. Moreover, to alleviate the data deficiency issue, a data augmentation strategy is employed for training the HNN. In order to evaluate its performance, the proposed HNN-based preselection operator is embedded into two surrogate-assisted evolutionary algorithms. Experimental results on two benchmark test suites and three real-world problems with up to 11 objectives and 150 decision variables involving seven state-of-the-art algorithms demonstrate the effectiveness of the proposed method. IEEE

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Register pressure sensitive instruction speculative scheduling technology

引用

Jisuanji Yanjiu yu Fazhan/computer Research and Development 2009年第3期46卷 485-491页

作者： Huang, Lei Feng, Xiaobing Lü, Fang Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Graduate University Chinese Academy of Sciences Beijing 100049 China

Speculation is an important method to overcome control flow constraints during instruction scheduling. On the one hand, speculation can exploit more instruction-level parallelism and improve performance. However, on the other hand, it may also lengthen the live range of variables and increase the register pressure, which in turn results in spilling some variables to memory and deteriorating the performance. Previous work on register pressure sensitive instruction scheduling generally scheduled instructions conservatively when there were too many live variables in the scheduling region. But actually different variables have different spilling costs and different impacts on performance. Here a register pressure sensitive speculative instruction scheduling technology is presented, which not only considers the count of live variables, but also analyzes the benefits and the spilling costs brought by instructions' speculative motions. The decrement of cycles in critical path is calculated as benefit, while the spilled variables are predicted and their spilling cost is used as cost. Only the speculative motion with benefit greater than the cost is permitted in our method. This algorithm has been implemented in Godson Compiler for MIPS architecture. Experiment result shows that the method in this paper can obtain 1.44% speedup on average relative to its register pressure insensitive counterpart on SPEC CPU2000INT benchmarks.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Learning from pseudo lesion: A self-supervised framework for covid-19 diagnosis

arXiv

引用

arXiv 2021年

作者： Li, Zhongliang Jin, Zhihao Li, Xuechen Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The Coronavirus disease 2019 (COVID-19) has rapidly spread all over the world since its first report in December 2019 and thoracic computed tomography (CT) has become one of the main tools for its diagnosis. In recent years, deep learning-based approaches have shown impressive performance in myriad image recognition tasks. However, they usually require a large number of annotated data for training. Inspired by Ground Glass Opacity (GGO), a common finding in COIVD-19 patient's CT scans, we proposed in this paper a novel self-supervised pretraining method based on pseudo lesions generation and restoration for COVID-19 diagnosis. We used Perlin noise, a gradient noise based mathematical model, to generate lesion-like patterns, which were then randomly pasted to the lung regions of normal CT images to generate pseudo COVID-19 images. The pairs of normal and pseudo COVID-19 images were then used to train an encoder-decoder architecture based U-Net for image restoration, which does not require any labelled data. The pretrained encoder was then fine-tuned using labelled data for COVID-19 diagnosis task. Two public COVID- 19 diagnosis datasets made up of CT images were employed for evaluation. Comprehensive experimental results demonstrated that the proposed self-supervised learning approach could extract better feature representation for COVID-19 diagnosis and the accuracy of the proposed method outperformed the supervised model pretrained on large scale images by 6.57% and 3.03% on SARS-CoV-2 dataset and Jinan COVID-19 dataset, respectively. © 2021, CC BY-NC-SA.

关键词： Coronavirus

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：