检索结果-内蒙古大学图书馆

2nd International Conference on Electronics, Communications and Information technology, CECIT 2021

作者： Hu, Yangyi Institute for Quantum Information State Key Laboratory of High Performance Computing National University of Defense Technology College of Computer Science and Technology Changsha410073 China

ISBN: (纸本)9781665437578

It is well known that the minimum adversarial distortion associated with a specific sample x0 reflects the local robustness of neural networks. However, it is intractable to solve the optimization problem related to the minimum adversarial distortion for general neural network cause it is non-convex. Works have studied the lower bound or upper bound of the minimum adversarial distortion to give a robustness metrics for neural networks, such as CLEVER score and CW attack. In this paper, we provide a formal robustness guarantee to transform the robustness analysis into two sub-problems: (1), compute out the maximum of the objective function gt* (rt);(2), generate a sequence {rth} s.t. limn→∞ rth is the minimum adversarial distortion for targeted attack. Based on this transformation, we propose an efficient and effective algorithm to directly estimate the instance-specific minimum adversarial distortion on the norm of the input manipulation required to change the classifier decision. Experimental results on two data-sets, MNIST and CIFAR, show that our measure of robustness is between the lower bound given by CLEVER and the upper bound by CW, indicating our approach gives a precise measure of the robustness of neural network. In addition, the powerful mathematical technique Extreme Value Estimation enables our algorithm computationally feasible for large neural networks. To the best of our knowledge, our algorithm is the first attack-independent approach to directly evaluate the minimum adversarial distortion as a robustness metric for neural network. © 2021 IEEE.

关键词： Estimation

来源：评论

学校读者我要写书评

暂无评论

The research on the measurement of water quality based on reflection cavity 38

The research on the measurement of water quality based on re...

引用

38th International Cosmic Ray Conference, ICRC 2023

作者： Tang, Yiyue Chen, Xinxin Zhang, Juntao Zhang, Qinghong Li, Xiurong Zhu, Fengrong Chen, Long School of Physical Science and Technology Southwest Jiaotong University Sichuan Province Chengdu611756 China Key Laboratory of Particle Astrophyics Experimental Physics Division Computing Center Institute of High Energy Physics Chinese Academy of Sciences Beijing100049 China

The passage of high-energy particles through water, air, and some other similar media produces Cherenkov light. Cherenkov detectors are widely used for detecting primary high-energy cosmic rays or gamma rays. The quality of the media is important for the experiments because the contaminants can absorb the light and reduce the precision of the reconstruction of the extensive air showers. Here we developed a method, similar to the integrating ring-down spectroscopy for evaluating the water quality. This method induced the laser as light source, the bucket with high reflective diffused material in the inner wall to reflect the light, photomultiplier tube (PMT) to record the waveform of light signal. We choose copper sulfate solution to find the relationship between solution concentration, the attenuation length of water, and the reflectivity of inner-wall material. The results proved the feasibility of the reflection cavity. This method can also be applied on the monitor of atmosphere, water pollution and cave safety, etc. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Cosmic ray detectors

来源：评论

学校读者我要写书评

暂无评论

Explicitly represent the boundary of ReLU NN as a classifier and measure its robustness 2

Explicitly represent the boundary of ReLU NN as a classifier...

引用

2nd International Conference on Electronics, Communications and Information technology, CECIT 2021

ISBN: (纸本)9781665437578

Adversarial examples pose a great threat to the application of neural network as a classifier in areas with high security requirements. Intuitively, the adversarial property of neural network is closely related to the boundary. However, works barely give a rigorous description of it. This paper for the first time studies the boundary of ReLU NN, which separates the sample space into distinct cells, each of which belongs to the same class. During the demonstration, we discuss the algebraic property of border points upon the separating boundary and the topological difference between border points and odd ones. We derive Theorem III.7 to give a rigorous, comprehensive and concise description on the boundary of ReLU NN. Furthermore, an algorithm, based on the description, is proposed to give a standard and exact metric for the local robustness of ReLU NN. This metric gives the local adversarial property of NN and reflects some aspects of its security performance, i.e. the nimimum distortion needed to craft an adversarial example. To the best of our knowledge, this is the first work proposed to give a rigorous and example-specific metric for the local robustness of ReLU NN. © 2021 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Symbolic Verification of Fuzzy Logic Models

Symbolic Verification of Fuzzy Logic Models

引用

IEEE International Conference on Automated Software Engineering (ASE)

作者： Siang Zhao Zhongyang Li Zhenbang Chen Ji Wang College of Computer National University of Defense Technology China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China State Key Laboratory of High Performance Computing National University of Defense Technology China

Fuzzy logic is widely applied in various applications. However, verifying the correctness of fuzzy logic models can be difficult. This extended abstract presents our ongoing work on verifying fuzzy logic models. We treat a fuzzy logic model as a program and propose a verification method based on symbolic execution for fuzzy logic models. We have developed and implemented the environment models for the common functions and the inference rules in fuzzy logic models. Our preliminary evaluation shows the potential of our verification method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

high-throughput studies and machine learning for design of β titanium alloys with optimum properties

引用

Transactions of Nonferrous Metals Society of China 2024年第10期34卷 3194-3207页

作者： Wei-min CHEN Jin-feng LING Kewu BAI Kai-hong ZHENG Fu-xing YIN Li-jun ZHANG Yong DU Guangdong Provincial Key Laboratory of Metal Toughening Technology and Application National Engineering Research Center of Powder Metallurgy of Titanium&Rare MetalsInstitute of New MaterialsGuangdong Academy of SciencesGuangzhou 510650China Institute of Advanced Wear&Corrosion Resistant and Functional Materials Jinan UniversityGuangzhou 510632China Institute of High Performance Computing Agency for ScienceTechnology and Research138632Singapore State Key Laboratory of Powder Metallurgy Central South UniversityChangsha 410083China

Based on experimental data,machine learning(ML) models for Young's modulus,hardness,and hot-working ability of Ti-based alloys were *** the models,the interdiffusion and mechanical property data were high-throughput re-evaluated from composition variations and nanoindentation data of diffusion ***,the Ti-(22±0.5)at.%Nb-(30±0.5)at.%Zr-(4±0.5)at.%Cr(TNZC) alloy with a single body-centered cubic(BCC) phase was screened in an interactive *** experimental results exhibited a relatively low Young's modulus of(58±4) GPa,high nanohardness of(3.4±0.2) GPa,high microhardness of HV(520±5),high compressive yield strength of(1220±18) MPa,large plastic strain greater than 30%,and superior dry-and wet-wear *** work demonstrates that ML combined with high-throughput analytic approaches can offer a powerful tool to accelerate the design of multicomponent Ti alloys with desired ***,it is indicated that TNZC alloy is an attractive candidate for biomedical applications.

关键词： high-throughput machine learning Ti-based alloys diffusion couple mechanical properties wear behavior

来源：评论

学校读者我要写书评

暂无评论

The Variable-Step L1 Scheme Preserving a Compatible Energy Law for Time-Fractional Allen-Cahn Equation

引用

Numerical Mathematics(Theory,Methods and Applications) 2022年第4期15卷 1128-1146页

作者： Hong-Lin Liao Xiaohan Zhu Jindi Wang MIIT Key Laboratory of Mathematical Modelling and High Performance Computing of Air Vehicles Nanjing 211106P.R.China School of Mathematics Nanjing University of Aeronautics and Astronautics211106P.R.China School of Mathematics and Computational Science Xiangtan UniversityXiangtan 411105P.R.China

In this work,we revisit the adaptive L1 time-stepping scheme for solving the time-fractional Allen-Cahn equation in the Caputo’s *** L1 implicit scheme is shown to preserve a variational energy dissipation law on arbitrary nonuniform time meshes by using the recent discrete analysis tools,i.e.,the discrete orthogonal convolution kernels and discrete complementary convolution *** the discrete embedding techniques and the fractional Gronwall inequality are applied to establish an L^(2)norm error estimate on nonuniform time *** adaptive time-stepping strategy according to the dynamical feature of the system is presented to capture the multi-scale behaviors and to improve the computational performance.

关键词： Time-fractional Allen-Cahn equation adaptive L1 scheme variational energy dissipation law orthogonal convolution kernels complementary convolution kernels

来源：评论

学校读者我要写书评

暂无评论

DSGA: Distractor-Suppressing Graph Attention for Multi-object Tracking 22

DSGA: Distractor-Suppressing Graph Attention for Multi-objec...

引用

Proceedings of the 8th International Conference on Robotics and Artificial Intelligence

作者： Guangjie Gao Yan Gao Liyang Xu Huibin Tan Yuhua Tang Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology China Chinese Institute of Electronics China

ISBN: (纸本)9781450397544

Multiple object tracking (MOT) methods based on single object tracking are of great interest because of their ability to balance efficiency and performance on the strength of the localization capability of single-target tracking. However, most of the single object tracking methods only distinguish foreground and background. They are susceptible to the influence of similar interfering objects during localization, while in multiple object tracking scenarios, there are more interfering objects and the influence is more severe. Therefore, we propose a Distractor-Suppressing Graph Attention (DSGA) to learn more discriminative attention by reducing the influence of distractors on learning attention weight features. Furthermore, DSGA is embedded into the basic MOT framework “SiamMOT” formed as DSGA-SiamMOT and applied to multiple object tracking to verify its effectiveness. We conduct experiments on the MOT Challenge benchmark with "public detection", and obtain MOTA 66.65%, IDF1 62.2% accuracy on the MOT17 dataset with 14fps.

关键词： graph attention mot sot distractor suppressing

来源：评论

学校读者我要写书评

暂无评论

Romat: Role-Based Multi-Agent Transformer for Generalizable Heterogeneous Cooperation

SSRN

引用

SSRN 2023年

作者： Wang, Dongzi Zhong, Fangwei Wen, Muning Li, Minglong Peng, Yuanxi Li, Teng Yang, Yaodong State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha China Peking University Beijing China Shanghai China

Multi-task multi-agent systems (MASs) are challenging to model because they involve heterogeneous agents with different behavior patterns that need to cooperate across various tasks. Existing networks for single-agent policies are not suitable for this setting, as they cannot share policies among agents without losing task-specific performance. We propose a novel framework called Role-based Multi-Agent Transformer (RoMAT), which uses a sequence modeling technique and a role-based actor to enable agents to adapt to different tasks and roles in MASs. RoMAT has a modular model architecture, where backbone networks are shared by all agents, but a small part of the parameters (role-based actor) is independent, depending on the agents’ exclusive structures. We evaluate RoMAT on several benchmark tasks and show that it can capture the behavior patterns of heterogeneous agents and achieve better performance and generalization than other methods in both single and multi-task settings. © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE STOCHASTIC GRADIENT ALGORITHM FOR BLACK-BOX MULTI-OBJECTIVE LEARNING 12

ADAPTIVE STOCHASTIC GRADIENT ALGORITHM FOR BLACK-BOX MULTI-O...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Ye, Feiyang Lyu, Yueming Wang, Xuehao Zhang, Yu Tsang, Ivor W. Department of Computer Science and Engineering Southern University of Science and Technology China Australian Artificial Intelligence Institute University of Technology Sydney Australia Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore Shanghai Artificial Intelligence Laboratory China School of Computer Science and Engineering Nanyang Technological University Singapore

Multi-objective optimization (MOO) has become an influential framework for various machine learning problems, including reinforcement learning and multitask learning. In this paper, we study the black-box multi-objective optimization problem, where we aim to optimize multiple potentially conflicting objectives with function queries only. To address this challenging problem and find a Pareto optimal solution or the Pareto stationary solution, we propose a novel adaptive stochastic gradient algorithm for black-box MOO, called ASMG. Specifically, we use the stochastic gradient approximation method to obtain the gradient for the distribution parameters of the Gaussian smoothed MOO with function queries only. Subsequently, an adaptive weight is employed to aggregate all stochastic gradients to optimize all objective functions effectively. Theoretically, we explicitly provide the connection between the original MOO problem and the corresponding Gaussian smoothed MOO problem and prove the convergence rate for the proposed ASMG algorithm in both convex and non-convex scenarios. Empirically, the proposed ASMG method achieves competitive performance on multiple numerical benchmark problems. Additionally, the state-of-the-art performance on the black-box multi-task learning problem demonstrates the effectiveness of the proposed ASMG method. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Latency-aware Partial Task Offloading in Collaborative Edge computing 26

Latency-aware Partial Task Offloading in Collaborative Edge ...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Gao, Yingmeng Zhu, Jie Huang, Haiping Chen, Chen Nanjing University of Posts & Telecommunications Nanjing210003 China Academy of Sciences State Key Laboratory Chinese of Computer Architecture Institute of Computing Technology Beijing100864 China Jiangsu High Technology Reasearch Key Laboratory of Wireless Sensor Networks Nanjing210023 China Nanjing University of Aeronautics and Astronautics Nanjing210016 China

ISBN: (纸本)9798350331684

When it comes to the fifth generation, collaborative edge computing is preferred for offloading computation-intensive tasks of low-latency applications in Internet of Things. In this paper, we consider the partial task offloading problem where tasks can be divided into subtasks and offloaded to nearby devices. The flow scheduling problem is integrated in the offloading process, i.e., multiple and conflicting route paths are considered. We propose the latency-aware partial task offloading framework (LaPTOF) for the considered problem. LaPTOF integrates a weighted priority ranking strategy (WPRS) which generates multiple solutions with different weights on task arrival time and the task processing time. A feasible solution generation method (FSGM) is designed where the best offloaded proportion of tasks are computed, and the appropriate offloaded devices and offload paths are determined. The proposed LaPTOF has an advantage in providing a scheduling plan that minimizes total completion time of task offloading in a shorter duration. The experimental results show that the proposal is suitable for the considered problem compared with JPOFH and its variants on both effectiveness and efficiency. © 2023 IEEE.

关键词： Internet of things

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：