检索结果-内蒙古大学图书馆

Differentially Private Online Federated Learning with Correlated Noise

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Jiaojiao Zhu, Linglingzhi Johansson, Mikael Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology StockholmSE-100 44 Sweden Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong

We introduce a novel differentially private algorithm for online federated learning that employs temporally correlated noise to enhance utility while ensuring privacy of continuously released models. To address challenges posed by DP noise and local updates with streaming non-iid data, we develop a perturbed iterate analysis to control the impact of the DP noise on the utility. Moreover, we demonstrate how the drift errors from local updates can be effectively managed under a quasi-strong convexity condition. Subject to an (ϵ, δ)DP budget, we establish a dynamic regret bound over the entire time horizon, quantifying the impact of key parameters and the intensity of changes in dynamic environments. Numerical experiments confirm the efficacy of the proposed algorithm. © 2024, CC BY.

关键词： Federated learning

Exploring the use of deep learning in task-flexible ILC

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Vinjarapu, Anantha Sai Hariharan Broens, Yorick Butler, Hans Tóth, Roland The Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands The Systems and Control Laboratory Institute for Computer Science and Control Hungary Asml Veldhoven Netherlands

Growing demands in today's industry results in increasingly stringent performance and throughput specifications. For accurate positioning of high-precision motion systems, feedforward control plays a crucial role. Nonetheless, conventional model-based feedforward approaches are no longer sufficient to satisfy the challenging performance requirements. An attractive method for systems with repetitive motion tasks is iterative learning control (ILC) due to its superior performance. However, for systems with non-repetitive motion tasks, ILC is generally not applicable, despite of some recent promising advances. In this paper, we aim to explore the use of deep learning to address the task flexibility constraint of ILC. For this purpose, a novel Task Analogy based Imitation Learning (TAIL)-ILC approach is developed. To benchmark the performance of the proposed approach, a simulation study is presented which compares the TAIL-ILC to classical model-based feedforward strategies and existing learning-based approaches, such as neural network based feedforward *** Codes 37M15 © 2023, CC BY.

关键词： Feedforward control

Dissipative Avoidance Feedback for Reactive Navigation Under Second-Order Dynamics

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Smaili, Lyes Tang, Zhiqi Berkane, Soulaimane Hamel, Tarek Department of Computer Science and Engineering University of Quebec in Outaouais GatineauQC Canada Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology StockholmSE-10044 Sweden Department of Electrical Engineering Lakehead University ON Canada France

This paper addresses the problem of autonomous robot navigation in unknown, obstacle-filled environments with second-order dynamics by proposing a Dissipative Avoidance Feedback (DAF). Compared to the Artificial Potential Field (APF), which primarily uses repulsive forces based on position, DAF employs a dissipative feedback mechanism that accounts for both position and velocity, contributing to smoother and more natural obstacle avoidance. The proposed continuously differentiable controller solves the motion-to-goal problem while guaranteeing collision-free navigation by using the robot’s state and local obstacle distance information. We show that the controller guarantees safe navigation in generic n-dimensional environments and that all undesired ω-limit points are unstable under certain controlled curvature conditions. Designed for real-time implementation, DAF requires only locally measured data from limited-range sensors (e.g., LiDAR, depth cameras), making it particularly effective for robots navigating unknown workspaces. Simulations in 2D and 3D environments are conducted to validate the theoretical results and to showcase the effectiveness of our approach. © 2024, CC BY.

关键词： Feedback

An Efficient Medical Image Deep Fusion Model Based on Convolutional Neural Networks

学校读者我要写书评

暂无评论

computers, Materials & Continua 2023年第2期74卷 2905-2925页

作者： Walid El-Shafai Noha A.El-Hag Ahmed Sedik Ghada Elbanby Fathi E.Abd El-Samie Naglaa F.Soliman Hussah Nasser AlEisa Mohammed E.Abdel Samea Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Higher Institute of Commercial Science Management Information SystemsEl-Mahala El-KobraEgypt Department of the Robotics and Intelligent Machines Faculty of Artificial IntelligenceKafrelsheikh UniversityKafr El-SheikhEgypt Department of Industrial Electronics and Control Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadhSaudi Arabia Medical Imaging and Interventional Radiology National Liver InstituteMenoufia UniversityEgypt

Medical image fusion is considered the best method for obtaining one image with rich details for efficient medical diagnosis and *** learning provides a high performance for several medical image analysis *** paper proposes a deep learning model for the medical image fusion *** model depends on Convolutional Neural Network(CNN).The basic idea of the proposed model is to extract features from both CT and MR ***,an additional process is executed on the extracted *** that,the fused feature map is reconstructed to obtain the resulting fused ***,the quality of the resulting fused image is enhanced by various enhancement techniques such as Histogram Matching(HM),Histogram Equalization(HE),fuzzy technique,fuzzy type,and Contrast Limited Histogram Equalization(CLAHE).The performance of the proposed fusion-based CNN model is measured by various metrics of the fusion and enhancement *** realistic datasets of different modalities and diseases are tested and ***,real datasets are tested in the simulation analysis.

关键词： Image fusion CNN deep learning feature extraction evaluation metrics medical diagnosis

When Does Sora Show:The Beginning of TAO to Imaginative Intelligence and Scenarios engineering

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 809-815页

作者： Fei-Yue Wang Qinghai Miao Lingxi Li Qinghua Ni Xuan Li Juanjuan Li Lili Fan Yonglin Tian Qing-Long Han School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Department of Electrical and Computer Engineering Indiana University-Purdue University IndianapolisIndianapolisIN 46202USA Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Virtual Reality Fundamental Research Laboratory Department of Mathematics and TheoriesPeng Cheng LaboratoryShenzhen 518000China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia

DURING our discussion at workshops for writing“What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence”[1],we had expected the next milestone for Artificial Intelligence(AI)would be in the direction of Imaginative Intelligence(II),i.e.,something similar to automatic wordsto-videos generation or intelligent digital movies/theater technology that could be used for conducting new“Artificiofactual Experiments”[2]to replace conventional“Counterfactual Experiments”in scientific research and technical development for both natural and social studies[2]-[6].Now we have OpenAI’s Sora,so soon,but this is not the final,actually far away,and it is just the beginning.

关键词： something Intelligence replace

A Study of Two Types of Introductory Exercise Problems for Network Programming Learning with Python 23

学校读者我要写书评

暂无评论

A Study of Two Types of Introductory Exercise Problems for N...

11th International Conference on computer and Communications Management, ICCCM 2023

作者： Lu, Xiqin Funabiki, Nobuo Ueda, Kiyoshi Kao, Wen-Chung Department of Information and Communication Systems Distributed System Design Lab. Okayama University Okayama Japan Department of Computer Science Control Software Lab. Nihon University Koriyama Japan Department of Electrical Engineering National Taiwan Normal University Taipei Taiwan

ISBN: (纸本)9798400707735

Network programming is the act of writing computer codes for communications between programs or processes in different computers across networks. It is crucial for applications and services using networks, including e-commerce, gaming, and social media. However, university courses of educating it are very limited. As a result, it has become important to develop and offer IT tools to support self-studies of network programming by novices. In this paper, we present a study of two types of introductory exercise problems, namely, Grammar-concept Understanding Problem (GUP) and Comment Insertion Problem (CIP), for self-studies of five basic network protocols of TCP/IP, ARP, SMTP, POP3, and SSH with Python. A GUP instance requests to answer the keyword such as a library function in the given source code that corresponds to the grammar concept described in the question. A CIP instance requests to insert the comment at each blank of the code. String matching is adopted to mark any answer at the browser-based answer interface. Through solving them, it is expected to understand the meaning of important words and the code structure for network programming. As preliminary evaluations, we generated six GUP and CIP instances respectively, and assigned them to 10 students in Okayama University, Japan. The results confirmed that the proposal is proper for novices to learn network programming with Python. © 2023 ACM.

关键词： Python

Distributed Optimization via Gradient Descent with Event-Triggered Zooming Over Quantized Communication

学校读者我要写书评

暂无评论

Distributed Optimization via Gradient Descent with Event-Tri...

IEEE Conference on Decision and control

作者： Apostolos I. Rikos Wei Jiang Themistoklis Charalambous Karl H. Johansson Department of Electrical and Computer Engineering Division of Systems Engineering Boston University Boston MA US Department of Electrical and Computer Engineering School of Engineering University of Cyprus Aalto University Nicosia Cyprus Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Division of Decision and Control Systems KTH Royal Institute of Technologyy Stockholm Sweden

In this paper, we study unconstrained distributed optimization strongly convex problems, in which the exchange of information in the network is captured by a directed graph topology over digital channels that have limited capacity (and hence information should be quantized). Distributed methods in which nodes use quantized communication yield a solution at the proximity of the optimal solution, hence reaching an error floor that depends on the quantization level used; the finer the quantization the lower the error floor. However, it is not possible to determine in advance the optimal quantization level that ensures specific performance guarantees (such as achieving an error floor below a predefined threshold). Choosing a very small quantization level that would guarantee the desired performance, requires information packets of very large size, which is not desirable (could increase the probability of packet losses, increase delays, etc) and often not feasible due to the limited capacity of the channels available. In order to obtain a communication-efficient distributed solution and a sufficiently close proximity to the optimal solution, we propose a quantized distributed optimization algorithm that converges in a finite number of steps and is able to adjust the quantization level accordingly. The proposed solution uses a finite-time distributed optimization protocol to find a solution to the problem for a given quantization level in a finite number of steps and keeps refining the quantization level until the difference in the solution between two successive solutions with different quantization levels is below a certain pre-specified threshold. Therefore, the proposed algorithm progressively refines the quantization level, thus eventually achieving low error floor with a reduced communication burden. The performance gains of the proposed algorithm are demonstrated via illustrative examples.

关键词：

Low-Complexity control for a Class of Uncertain MIMO Nonlinear systems under Generalized Time-Varying Output Constraints (extended version)

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mehdifar, Farhad Lindemann, Lars Bechlioulis, Charalampos P. Dimarogonas, Dimos V. Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Thomas Lord Department of Computer Science University of Southern California Los AngelesCA United States Division of Systems and Control Department of Electrical and Computer Engineering University of Patras Patra Greece

This paper introduces a novel control framework to address the satisfaction of multiple time-varying output constraints in uncertain high-order MIMO nonlinear control systems. Unlike existing methods, which often assume that the constraints are always decoupled and feasible, our approach can handle coupled time-varying constraints even in the presence of potential infeasibilities. First, it is shown that satisfying multiple constraints essentially boils down to ensuring the positivity of a scalar variable, representing the signed distance from the boundary of the time-varying output-constrained set. To achieve this, a single consolidating constraint is designed that, when satisfied, guarantees convergence to and invariance of the time-varying output-constrained set within a user-defined finite time. Next, a novel robust and low-complexity feedback controller is proposed to ensure the satisfaction of the consolidating constraint. Additionally, we provide a mechanism for online modification of the consolidating constraint to find a least violating solution when the constraints become mutually infeasible for some time. Finally, simulation examples of trajectory and region tracking for a mobile robot validate the proposed approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Feedback control

Finite Sample Analysis for a Class of Subspace Identification Methods

学校读者我要写书评

暂无评论

Finite Sample Analysis for a Class of Subspace Identificatio...

IEEE Conference on Decision and control

作者： Jiabao He Ingvar Ziemann Cristian R. Rojas Håkan Hjalmarsson Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden University of Pennsylvania Philadelphia PA USA

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

While subspace identification methods (SIMs) are appealing due to their simple parameterization for MIMO systems and robust numerical realizations, a comprehensive statistical analysis of SIMs remains an open problem, especially in the non-asymptotic regime. In this work, we provide a finite sample analysis for a class of SIMs, which reveals that the convergence rates for estimating Markov parameters and system matrices are $\mathcal{O}(1 / \sqrt{N})$, in line with classical asymptotic results. Based on the observation that the model format in classical SIMs is non-causal because of a projection step, we choose a parsimonious SIM that bypasses the projection step and strictly enforces a causal model to facilitate the analysis, where a bank of ARX models are estimated in parallel. Leveraging recent results from a finite sample analysis of an individual ARX model, we obtain a union error bound for an array of ARX models and proceed to derive error bounds for system matrices using robustness results for the singular value decomposition.

关键词： Analytical models Statistical analysis Robustness MIMO Matrix decomposition Singular value decomposition Convergence