检索结果-内蒙古大学图书馆

Evolution and Effectiveness of Loss Functions in Generative Adversarial Networks

China Communications 2021年第10期18卷 45-76页

作者： Ali Syed Saqlain Fang Fang Tanvir Ahmad Liyun Wang Zain-ul Abidin School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China Department of Computer Science Portland State UniversityPortland 97207U.S. School of Information and Communication Engineering South West Jiaotong UniversityChengdu 610031China

Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational *** improve the generating ability of GANs,various loss functions are introduced to measure the degree of similarity between the samples generated by the generator and the real data samples,and the effectiveness of the loss functions in improving the generating ability of *** this paper,we present a detailed survey for the loss functions used in GANs,and provide a critical analysis on the pros and cons of these loss ***,the basic theory of GANs along with the training mechanism are ***,the most commonly used loss functions in GANs are introduced and ***,the experimental analyses and comparison of these loss functions are presented in different GAN ***,several suggestions on choosing suitable loss functions for image synthesis tasks are given.

关键词： loss functions deep learning machine learning unsupervised learning generative adversarial networks(GANs) image synthesis

来源：评论

学校读者我要写书评

暂无评论

MRI Brain Tumor Classification Using Optimized APSO-LLRBFNN 2

MRI Brain Tumor Classification Using Optimized APSO-LLRBFNN

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Krishna, Tiruveedula Gopi Sreenivas, Nune Ajay Kumar, M. Reddy, Chandra Sekhar Rathee, Davinder Sing Urgessa, Teklu College of Electrical Engineering and Computing Adama Science and Technology University Department of Computer Science and Engineering Adama Ethiopia Andhra Loyala institute of Engineering and Technology Department of Electrical and Electronics Engineering Vijayawada India College of Electrical Engineering and Computing Adama Science and Technology University Department of Electrical Power and Control Engineering Adama Ethiopia College of Electrical Engineering and Computing Adama Science and Technology University Department of ECE Adama Ethiopia

ISBN: (纸本)9798331505745

The research presents a new efficient machine learning method to classify brain tumors because this task remains vital in fighting the high incidence of brain cancers. The proposed approach unites all its operations including image segmentation with feature extraction and classification into a single processing system. This study uses Particle Swarm Optimization (PSO) and Adaptive PSO (APSO) methodologies to optimize Locally Linear Radial Basis Function Neural Network (LLRBFNN) resulting in PSO-LLRBFNN and APSO-LLRBFNN model implementations. The research examined the optimized APSO-LLRBFNN models against Support Vector Machines (SVM) and Least Mean Squares (LMS) based LLRBFNN classifier methods. Results from experiments show that APSO-LLRBFNN gives superior outcomes with 98.93% accuracy and takes 12.23 seconds for execution, which surpasses currently available methods. © 2025 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Towards an Integrated Framework for Fugitive Methane Source Localization and Monitoring in a Wireless Sensor Network

Towards an Integrated Framework for Fugitive Methane Source ...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Amira Al Jawhari Yasmine Souissi Jawhar Ghommam Yassine Jamoussi Faisal Mnif Department of Electrical and Computer Engineering College of Engineering Sultan Qaboos University Department of Engineering GUtech University Muscat Oman Laboratory of Control Energy Management (Cem-Lab) ENIS Tunisa Departement of Computer Science College of Science SQU

Gas leaks are the main cause of industrial fires and accidents. These cause countless fatalities, equipment damage, and other severe environmental effects. In this paper, we provide a framework for the monitoring and detection of methane leakage using a diffusion model based on the gas diffusion theory. Given that centralized Least Square methods are not efficient and robust as they require the gathering and processing of large-scale measurements on a central node. We propose a detection technique which makes use of the distributed (Non-linear) least squares method to overcome this problem. Then, a network of connected methane sensors is used to detect gas leaks. In order to estimate the parameters of the diffusive model for the gas leakage on each sensor node, a distributed recursive estimator of the consensus plus an innovation type technique is used. The characteristics being estimated include the gas source’s distance, which will be effectively triangulated to determine the source’s precise location. The targeted location is subsequently estimated using a location dispersed algorithm-based LS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Approximation of the Quotient of Two Gaussian Densities for Multiple-Model Smoothing 26

On the Approximation of the Quotient of Two Gaussian Densiti...

引用

26th International Conference on Information Fusion, FUSION 2023

作者： Liu, Yi Li, Xi Yang, Le Mihaylova, Lyudmila Xue, Yanbo University of Canterbury Department of Electrical and Computer Engineering Christchurch New Zealand National University of Defense Technology State Key Lab of Complex Electromagnetic Environment Effects on Electronics and Information Systems Changsha China University of Sheffield Department of Automatic Control and System Engineering Sheffield United Kingdom Career Science Lab Beijing China

ISBN: (纸本)9798890344854

The quotient of two multivariate Gaussian densities can be written as an unnormalized Gaussian density, which has been applied in some recently developed multiple-model fixed-interval smoothing algorithms. However, this expression is invalid if instead of being positive definite, the covariance of the unnormalized Gaussian density is indefinite (i.e., it has both positive and negative eigenvalues) or undefined (i.e., computing it requires inverting a singular matrix). This paper considers approximating the quotient of two Gaussian densities in this case using two different approaches to mitigate the caused numerical problems. The first approach directly replaces the indefinite covariance of the unnormalized Gaussian density with a positive definite matrix nearest to it. The second approach computes the approximation through solving, using the natural gradient, an optimization problem with a Kullback-Leibler divergence-based cost function. This paper illustrates the application of the theoretical results by incorporating them into an existing smoothing method for jump Markov systems and utilizing the obtained smoothers to track a maneuvering target. © 2023 International Society of Information Fusion.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

State-Space Piece-Wise Affine System Identification with Online Deterministic Annealing

State-Space Piece-Wise Affine System Identification with Onl...

引用

European control Conference (ECC)

作者： Christos N. Mavridis Aris Kanellopoulos John S. Baras Karl Henrik Johansson Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Department of Electrical and Computer Engineering and the Institute for Systems Research University of Maryland College Park USA

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

We propose an online identification scheme for discrete-time piece-wise affine state-space models based on a system of adaptive algorithms running in two timescales. A stochastic approximation algorithm implements an online deterministic annealing scheme at a slow timescale, estimating the partition of the augmented state-input space that defines the switching signal. At the same time, an adaptive identification algorithm, running at a higher timescale, updates the parameters of the local models based on the estimate of the switching signal. Identifiability conditions for the switched system are discussed and convergence results are given based on the theory of two-timescale stochastic approximation. In contrast to standard identification algorithms for piece-wise affine systems, the proposed approach progressively estimates the number of modes needed and is appropriate for online system identification using sequential data acquisition. This progressive nature of the algorithm improves computational efficiency and provides real-time control over the performance-complexity trade-off, desired in practical applications. Experimental results validate the efficacy of the proposed methodology.

关键词： Switched systems Annealing Stochastic processes Switches Approximation algorithms Real-time systems System identification

来源：评论

学校读者我要写书评

暂无评论

Applying System Thinking to Learn from Accident of Modern Automatic control Systems

引用

Chinese Journal of Electronics 2025年第2期23卷 409-414页

作者： Ru Niu Yuan Cao Xiaocheng Ge Tao Tang State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China School of Electronics and Information Engineering National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Beijing China Department of Computer Science University of York York UK

Modern societies increasingly rely on automatic control systems. These systems are hardly pure technical systems; instead they are complex socio-technical systems, which consist of technical elements and social components. It is necessary to have a systematic approach to analyze these systems because it is growing evidence that accidents from these systems usually have complex causal factors which form an interconnected network of events, rather than a simple cause-effect chain. We take railway Train control systems (TCS) as an example to demonstrate the importance of the socio-technical approach to analyze the system. The paper presents an investigation of recent high-speed railway accident by applying STAMP - one of the most notable socio-technical system analysis techniques, outlines improvements to the system which could avoid similar accidents in the future. We also provide our valuable feedback for the use of STAMP.

关键词： Sociotechnical systems Analytical models Systematics Railway accidents Transportation Medical services Rail transportation Systems thinking Research and development Accidents

来源：评论

学校读者我要写书评

暂无评论

Simple and Optimal Sublinear Algorithms for Mean Estimation

arXiv

引用

arXiv 2024年

作者： Bertolotti, Beatrice Russo, Matteo Schwiegelshohn, Chris Shyam, Sudarshan Department of Computer Science Aarhus University Åbogade 34 Aarhus N8200 Denmark Department of Computer Control Management Engineering Sapienza University of Rome Via Ariosto 25 Rome00185 Italy

We study the sublinear multivariate mean estimation problem in d-dimensional Euclidean space. Specifically, we aim to find the mean µ of a ground point set A, which minimizes the sum of squared Euclidean distances of the points in A to µ. We first show that a multiplicative (1 + Ε) approximation to µ can be found with probability 1 − δ using O(Ε−1 log δ−1) many independent uniform random samples, and provide a matching lower bound. Furthermore, we give two sublinear time algorithms with optimal sample complexity for extracting a suitable approximate mean: 1. A gradient descent approach running in time O((Ε−1 + log log δ−1) · log δ−1 · d). It optimizes the geometric median objective while being significantly faster for our specific setting than all other known algorithms for this problem. 2. An order statistics and clustering approach running in time O ((Ε−1 + logγ δ−1) · log δ−1 · d) for any constant γ > 0. Throughout our analysis, we also generalize the familiar median-of-means estimator to the multivariate case, showing that the geometric median-of-means estimator achieves an optimal sample complexity for estimating µ, which may be of independent interest. © 2024, CC BY.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

Resilient distributed optimization under mobile malicious attacks

引用

IFAC-PapersOnLine 2023年第2期56卷 997-1002页

作者： Yuan Wang Changxin Liu Hideaki Ishii Karl Henrik Johansson Department of Robotics Hunan University Changsha China Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology and Digital Futures Stockholm Sweden Department of Computer Science Tokyo Institute of Technology Yokohama Japan

This article addresses the distributed optimization problem in the presence of malicious adversaries that can move within the network and induce faulty behaviors in the attacked nodes. We first investigate the vulnerabilities of a consensus-based secure distributed optimization protocol under mobile adversaries. Then, a modified resilient distributed optimization algorithm is proposed. We develop conditions on the network structure for both complete and non-complete directed graph cases, under which the proposed algorithm guarantees that the estimates by regular nodes converge to the convex combination of the minimizers of their local functions. Simulations are carried out to verify the effectiveness of our approach.

关键词： Fault-tolerant distributed optimization multi-agent systems network security mobile adversary agents

来源：评论

学校读者我要写书评

暂无评论

MRI Brain Tumor Classification Using Optimized APSO-LLRBFNN

MRI Brain Tumor Classification Using Optimized APSO-LLRBFNN

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Tiruveedula Gopi Krishna Nune Sreenivas M. Ajay Kumar Chandra Sekhar Reddy Davinder Sing Rathee Teklu Urgessa Department of Computer Science and Engineering College of Electrical Engineering and Computing Adama Science and Technology University Adama Ethiopia Department of Electrical and Electronics Engineering Andhra Loyala institute of Engineering and Technology Vijayawada India Department of Electrical Power and Control Engineering College of Electrical Engineering and Computing Adama Science and Technology University Adama Ethiopia Department of ECE College of Electrical Engineering and Computing Adama Science and Technology University Adama Ethiopia

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

关键词： Support vector machines Image segmentation Adaptation models Accuracy Magnetic resonance imaging Machine learning Feature extraction Brain modeling Data models Numerical models

来源：评论

学校读者我要写书评

暂无评论

Risk-Averse Learning with Delayed feedback

arXiv

引用

arXiv 2024年

作者： Wang, Siyi Wang, Zifan Johansson, Karl H. Hirche, Sandra Department of Electrical and Computer Engineering Technical University of Munich Munich80333 Germany Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

In real-world scenarios, the impacts of decisions may not manifest immediately. Taking these delays into account facilitates accurate assessment and management of risk in real-world environments, thereby ensuring the efficacy of strategies. In this paper, we investigate risk-averse learning using Conditional Value at Risk (CVaR) as risk measure, while incorporating delayed feedback with unknown but bounded delays. We develop two risk-averse learning algorithms that rely on one-point and two-point zeroth-order optimization approaches, respectively. The regret achieved by the algorithms is analyzed in terms of the cumulative delay and the number of total samplings. The results suggest that the two-point risk-averse learning achieves a smaller regret bound than the one-point algorithm. Furthermore, the one-point risk-averse learning algorithm attains sublinear regret under certain delay conditions, and the two-point risk-averse learning algorithm achieves sublinear regret with minimal restrictions on the delay. We provide numerical experiments on a dynamic pricing problem to demonstrate the performance of the proposed algorithms. © 2024, CC0.

关键词： Adversarial machine learning

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：