检索结果-内蒙古大学图书馆

2024 International Conference on Intelligent algorithms for Computational Intelligence Systems, IACIS 2024

作者： Yin, Jiaxing Guan, Yan Tian, Yufeng Wuhan Textile University College of Art and Design Wuhan China

ISBN: (纸本)9798350360660

The aging of the global population makes the age-friendly design a hot topic in the design field and society. A three-dimensional indoor elderly friendly design system based on adaptive genetic algorithm is proposed to create a safe, comfortable and convenient living environment for the elderly. This paper introduces the construction of adaptive genetic algorithm, including population initialization, parameter setting, adaptive mechanism and fitness function design. In addition, this paper also analyzes the requirements of aging-friendly design, and transforms these requirements into quantifiable design parameters, which are encoded into the chromosomes of genetic algorithm. The experimental results show that the processing time of AGA is obviously lower than that of SGA, the accuracy reaches 98.8%, and the stability remains above 90.6%. The user satisfaction score reaches 9.9, which shows the potential of the system in providing high-quality design solutions. © 2024 IEEE.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Machine Unlearning: An Overview of the Paradigm Shift in the Evolution of AI 21

Machine Unlearning: An Overview of the Paradigm Shift in the...

引用

21st International Learning and Technology Conference, L and T 2024

作者： Jaman, Layan Alsharabi, Reem Elkafrawy, Passent M. Effat University Effat College of Engineering Energy and Technology Research Center Computer Science Department Jeddah Saudi Arabia

ISBN: (纸本)9798350393569

The rapid advancements in artificial intelligence (AI) have primarily focused on the process of learning from data to acquire knowledge for smart systems. However, the concept of machine unlearning has emerged as a transformative paradigm shift in the field of AI, due to the amount of false information that have been learned over the past. Machine unlearning refers to the ability of AI systems to reverse or discard previously acquired knowledge or patterns, enabling them to adapt and refine their understanding in response to changing circumstances or new insights. This paper explores the concept of machine unlearning, its implications, methods, challenges, and potential applications. The paper begins by providing an overview of the traditional learning-based approaches in AI and the limitations they impose on system adaptability and agility. It then delves into the concept of machine unlearning, discussing various techniques and algorithms employed to remove or modify learned knowledge from AI models or datasets. © 2024 IEEE.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

adaptive Evolution Strategies for Stochastic Zeroth-Order Optimization

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2022年第5期6卷 1271-1285页

作者： He, Xiaoyu Zheng, Zibin Chen, Zefeng Zhou, Yuren Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore

We consider solving a class of unconstrained optimization problems in which only stochastic estimates of the objective functions are available. Existing stochastic optimization methods are mainly extended from gradient-based methods, faced with the challenges of noisy function evaluations, hardness in choosing step-sizes, and probably ill-conditioned landscapes. This paper presents a stochastic evolution strategy (SES) framework and several adaptation schemes to avoid these challenges. The SES framework combines the ideas of population sampling and minibatch sampling in exploiting the zeroth-order gradient information, efficiently reducing the noise in both data selection and gradient approximation. In addition, it admits approximating the gradients using a non-isotropic Gaussian distribution to better capture the curvature information of the landscapes. Based on this framework, we implement a step-size adaptation rule and two covariance matrix adaptation rules, where the former can automatically tune the step-sizes and the latter are intended to cope with ill-conditioning. For SES with certain fixed step-sizes, we establish a nearly optimal convergence rate over smooth landscapes. We also show that using the adaptive step-sizes allows convergence at a slightly slower rate but without the need to know the smoothness constant. Several numerical experiments on machine learning problems verify the above theoretical results and suggest that the adaptive SES methods show much promise.

关键词： Stochastic processes Optimization Smoothing methods Convergence Covariance matrices Computational modeling Training adaptive algorithms evolution strategies stochastic optimization zeroth-order optimization

来源：评论

学校读者我要写书评

暂无评论

Refining the Adaptivity Notion in the Huge Object Model 27

Refining the Adaptivity Notion in the Huge Object Model

引用

27th International Conference on Approximation algorithms for Combinatorial Optimization Problems, APPROX 2024 and the 28th International Conference on Randomization and Computation, RANDOM 2024

作者： Adar, Tomer Fischer, Eldar Technion – Israel Institute of Technology Haifa Israel

ISBN: (纸本)9783959773485

The Huge Object model for distribution testing, first defined by Goldreich and Ron in 2022, combines the features of classical string testing and distribution testing. In this model we are given access to independent samples from an unknown distribution P over the set of strings {0, 1}n but are only allowed to query a few bits from the samples. The distinction between adaptive and non-adaptive algorithms, which occurs naturally in the realm of string testing (while being irrelevant for classical distribution testing), plays a substantial role also in the Huge Object model. In this work we show that the full picture in the Huge Object model is much richer than just that of the adaptive vs. non-adaptive dichotomy. We define and investigate several models of adaptivity that lie between the fully-adaptive and the completely non-adaptive extremes. These models are naturally grounded by observing the querying process from each sample independently, and considering the "algorithmic flow" between them. For example, if we allow no information at all to cross over between samples (up to the final decision), then we obtain the locally bounded adaptive model, arguably the "least adaptive" one apart from being completely non-adaptive. A slightly stronger model allows only a "one-way" information flow. Even stronger (but still far from being fully adaptive) models follow by taking inspiration from the setting of streaming algorithms. To show that we indeed have a hierarchy, we prove a chain of exponential separations encompassing most of the models that we define. © Tomer Adar and Eldar Fischer.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Analytical adaptive Algorithm for Autonomous Race Driving 27

Analytical Adaptive Algorithm for Autonomous Race Driving

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Sambhu, Neil Katkoori, Srinivas University of South Florida Computer Science and Engineering Department FL33620 United States University of South Florida Department of Computer Science and Engineering FL33620 United States

ISBN: (纸本)9798331505929

Autonomous race driving is a difficult problem, as the driving algorithm needs to find unique maneuvers on the track to achieve the fastest lap time. To date and to the best of our knowledge, there exists no algorithm that supersedes human performance. In this work, we propose an analytical self-driving algorithm for race driving. The self-driving algorithm will use a baseline (i.e., generated a priori by manually driving on the track) for course correction while attempting to achieve the shortest lap time. The proposed algorithm iteratively determines the steer angle, throttle, and brake controls while adhering as close to the baseline, by computing deviations between (1) the predicted location at the next time step and (2) the baseline location closest to predicted. We report results for various fixed speeds to demonstrate the correctness of the algorithm. We then demonstrate more realistic adaptive driving that greedily increases the speed whenever the steering correction is small. The proposed algorithm is implemented and validated in the open-source CARLA Simulator v0.9.14. Experimental results for three different car models demonstrate that the adaptive algorithm is effective in achieving good lap times. © 2024 IEEE.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Fine-grained point cloud classification based on adaptive KNN algorithm 24

Fine-grained point cloud classification based on adaptive KN...

引用

2024 International Conference on Intelligent Perception and Pattern Recognition, IPPR 2024

作者： Liu, Lu Bai, Jing Yan, Hao School of Computer Science and Engineering North Minzu University China The Key Laboratory of images Graphics Intelligent Processing of State Ethnic Affairs Commission China

ISBN: (纸本)9798400707315

In point cloud deep learning, local feature aggregation is crucial to improve the performance of the model. The traditional KNN (K-Nearest Neighbors) method performs local feature aggregation by fixing the K value, but often performs poorly in the face of different local structural variations. In order to overcome these limitations, this study proposes an improved KNN method that adapts to the diversity of local regions of the point cloud by adaptively adjusting the neighborhood size in order to maintain feature diversity and accuracy in regions of varying importance. Specifically, in this paper, we dynamically adjust different neighborhood ranges according to the attention weights of individual points, thus ensuring that local features are effectively captured in both important as well as non-important regions. In addition, we conduct experiments on the FG3D and ModelNet40, point cloud datasets. The overall accuracy of AK-Net reaches 96.31%, 79.85%, and 82.38% in the experimental results on the three sub-datasets Airplane, Car, and Chair of FG3D, and 94.04% on ModelNet40. Therefore, the classification performance of AK-Net is superior. © 2024 Copyright held by the owner/author(s).

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Underwater Frequency Selection Algorithm Based on the Received Signal

Underwater Frequency Selection Algorithm Based on the Receiv...

引用

2025 IEEE Underwater Technology, UT 2025

作者： Alahmad, Raji Albaroudi, Mohammad Alraee, Abdullah Ishii, Kazuo Kyushu Institute of Technology Department of Human Intelligence Systems Fukuoka Kitakyushu Japan Kyushu Institute of Technology Department of Life Science and System Engineering Fukuoka Kitakyushu Japan

ISBN: (纸本)9798331534189

Underwater communication is widely regarded as one of the most significant challenges due to the unique physical properties of water. Among the available communication methods, radiofrequency communication offers higher data transmission rates than acoustic communication. However, higher frequencies suffer from substantial attenuation in water, making it difficult to achieve long-distance transmission. Addressing the tradeoff between transmission rate and communication distance is essential for achieving optimal performance. Unlike conventional systems that rely on fixed operating frequencies, this study introduces a dynamic frequency selection algorithm. This algorithm dynamically adjusts the operating frequency in real-time based on channel conditions and transmission rate feedback, ensuring a more adaptive and efficient communication system. To validate this approach, a dipole antenna with multiple impedance matching was designed and tested in a water tank environment. The experimental results revealed that bandwidth performance varied across different frequencies. Transmission rate analysis showed that higher frequencies provided higher data transmission over short distances. Conversely, lower frequencies exhibited better signal stability and reliability for long-distance communication due to their reduced attenuation. These findings highlight the importance of adaptive frequency selection in underwater radiofrequency communication, where a balance between transmission rate and communication distance must be achieved to support various operational requirements. © 2025 IEEE.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Faster adaptive Federated Learning 37

Faster Adaptive Federated Learning

引用

37th AAAI Conference on Artificial Intelligence (AAAI) / 35th Conference on Innovative Applications of Artificial Intelligence / 13th Symposium on Educational Advances in Artificial Intelligence

作者： Wu, Xidong Huang, Feihu Hu, Zhengmian Huang, Heng Univ Pittsburgh Elect & Comp Engn Pittsburgh PA 15213 USA Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China

ISBN: (纸本)9781577358800

Federated learning has attracted increasing attention with the emergence of distributed data. While extensive federated learning algorithms have been proposed for the non-convex distributed problem, federated learning in practice still faces numerous challenges, such as the large training iterations to converge since the sizes of models and datasets keep increasing, and the lack of adaptivity by SGD-based model updates. Meanwhile, the study of adaptive methods in federated learning is scarce and existing works either lack a complete theoretical convergence guarantee or have slow sample complexity. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on the momentum-based variancereduced technique in cross-silo FL. We first explore how to design the adaptive algorithm in the FL setting. By providing a counter-example, we prove that a simple combination of FL and adaptive methods could lead to divergence. More importantly, we provide a convergence analysis for our method and prove that our algorithm is the first adaptive FL algorithm to reach the best-known samples O(is an element of(-3)) and O(is an element of(-2)) communication rounds to find an is an element of-stationary point without large batches. The experimental results on the language modeling task and image classification task with heterogeneous data demonstrate the efficiency of our algorithms.

关键词： adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Modified Huber M-Estimate Function-Based Distributed Constrained adaptive Filtering Algorithm Over Sensor Network

引用

IEEE SENSORS JOURNAL 2022年第20期22卷 19567-19582页

作者： Xu, Wenjing Zhao, Haiquan Zhou, Lijun Southwest Jiaotong Univ Key Lab Magnet Suspens Technol & Maglev Vehicle Minist Educ Chengdu 610031 Peoples R China Southwest Jiaotong Univ Sch Elect Engn Chengdu 610031 Peoples R China

Most of the existing distributed adaptive filtering algorithms over wireless sensor networks (WSNs) are developed, aiming to solve unconstrained network optimization problems. However, in practice, the weight coefficients of the filter may need to satisfy a set of linear equations. Thus, a distributed adaptive algorithm that can solve the sensor network optimization problem under constraints is needed. Considering the possible impulsive interference in the observed signals, a novel robust distributed constrained adaptive algorithm called diffusion constrained least mean M-estimate (D-CLMM) is proposed by using the modified Huber function (MHF), which endows the network robustness to impulsive noise. The transient, steady-state performances and stability of the proposed D-CLMM are studied with the aid of some commonly used assumptions and verified by computer simulations. Moreover, the effectiveness of D-CLMM is verified in distributed parameter estimation and beamforming applications in non-Gaussian noise environments.

关键词： Sensors Optimization Wireless sensor networks adaptive algorithms Filtering algorithms adaptive systems Robustness Distributed constrained adaptive filtering M-estimate non-Gaussian noise performance analysis robust algorithm wireless sensor network (WSN)

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Control of Highly Deformable Robotic Endoscopes Using Proprioceptive Shape Feedback

Data-Driven Control of Highly Deformable Robotic Endoscopes ...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Lu, Yiang Zheng, Jixuan Liu, Yun-Hui T Stone Robotics Institute The Chinese University of Hong Kong Department of Mechanical and Automation Engineering Hong Kong Hong Kong Hong Kong Center for Logistics Robotics Hong Kong Hong Kong

ISBN: (纸本)9781665481090

In this paper, we introduce a versatile data-driven approach for servo-controlling the highly deformable robotic endoscope equipped with Draw Tower Gratings (DTGs). The advancement of perception and decision-making technologies is pivotal for enabling flexible robots to execute automatic procedures. However, modeling these robots presents a significant challenge due to their large deformations and susceptibility to environmental disturbances. To address this issue, we propose a robust adaptive control framework that leverages DTG-based proprioceptive shape feedback. This automatic paradigm can online estimate the unknown deformation model of the flexible robot based on function approximation (FA), while also accounting for unknown perturbations without prior identification. By employing the proposed FA-based adaptive algorithm, we can ensure the convergence of the shape control error. Experimental results validating a highly deformable flexible robot embedded with DTG sensors showcase the efficiency of the proposed control strategy in unknown scenarios. © 2024 IEEE.

关键词： adaptive algorithms

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：