检索结果-内蒙古大学图书馆

IEEE 5th Annual World AI IoT Congress (AIIoT)

作者： Chan, S. VT I PAC VTIRL Orlando FL 32810 USA

ISBN: (纸本)9798350387803;9798350387810

Energy consumption at the various steps of the Machine Learning (ML) model life cycle, as a constituent application of Artificial Intelligence (AI), is infrequently reported. While the Explainable AI (XAI) or Explainable ML (XML) movement has focused upon more explainable ML models, the AI Energy Consumption (AEC) facet has not progressed as rapidly and still remains quite translucent. For example, even the AEC ratios of the key AI stages (e.g., pre-training, fine-tuning, and inferencing) have not always accompanied the releases of new ML models. This lack of data has, perhaps, contributed to the dearth of analyses on effective compute (e.g., algorithmic efficiency versus hardware efficiency) for the newer models, and in modern times, AEC may be skewing to the inferencing side. This may necessitate revised architectures, particularly amidst the findings that generalized ML models for specific tasks have a much higher AEC when contrasted against task-specific ML models. It has also been reported that, within those same models, a higher number of parameters segues to a higher AEC. Higher accuracies also beget higher AECs, and "advanced anomaly detection" necessitates tasks that have an even higher AEC. Moreover, as it is now customary to run numerous instances of a pre-trained model over various instances in an ensemble fashion, the AEC is multiplied accordingly. Yet, there are opportunities to reduce AEC at the Metaheuristic Algorithm (MA) level (e.g., at the convolutional layer), and certain versatile constructs (that scale well across the AI stages) are amenable to such optimizations;furthermore, performance metric comparisons in the literature have, traditionally, been artificially constrained to a "fixed number of allowed function calls," and this might have led to misinterpretations of MA performance in Real World Scenario (RWS) paradigms. These misinterpretations can skew research directions, particularly for RWS Multiple Objective Large Scale Nonlinear Program

关键词： computational intelligence evolutionary computation nature-inspired metaheuristic inference energy consumption multiple objective large scale nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

A Many-objective evolutionary Algorithm Approach for Graph Visualization 18

A Many-objective Evolutionary Algorithm Approach for Graph V...

引用

18th Annual IEEE International Systems Conference (SysCon)

作者： Khan, Burhan Johnstone, Michael Creighton, Douglas Deakin Univ Inst Intelligent Syst Res & Innovat IISRI Geelong Vic 3217 Australia

ISBN: (纸本)9798350358810;9798350358803

Determining the layout of a graph from an aesthetic point-of-view is a challenging task and becomes difficult with the increase in complexity of a graph. Aesthetic attributes of graphs can be captured in terms of metrics such as the number of edge crossings, uniform edge lengths, visualization of loops in causal loop diagrams, and a minimum distance between neighboring nodes. These metrics are then used as objectives in an evolutionary algorithm to obtain the optimal set of trade-off solutions, leading to a pleasing layout. As the number of aesthetic measures could be more than three, we propose a framework based on a many-objective evolutionary algorithm to produce aesthetically pleasing graph layouts. The outcome of this approach is compared with the ForceAtlas2 force-directed layout algorithm and the proposed approach demonstrates better results for the objectives.

关键词： Causal-loop Diagram Aesthetics evolutionary computation Graph Layout Many-Objective Multi-Objective Optimization

来源：评论

学校读者我要写书评

暂无评论

A generalized evolutionary metaheuristic (GEM) algorithm for engineering optimization

引用

COGENT ENGINEERING 2024年第1期11卷

作者： Yang, Xin-She Middlesex Univ London Sch Sci & Technol London England

Many optimization problems in engineering and industrial design applications can be formulated as optimization problems with highly nonlinear objectives, subject to multiple complex constraints. Solving such optimization problems requires sophisticated algorithms and optimization techniques. A major trend in recent years is the use of nature-inspired metaheustic algorithms (NIMA). Despite the popularity of nature-inspired metaheuristic algorithms, there are still some challenging issues and open problems to be resolved. Two main issues related to current NIMAs are: there are over 540 algorithms in the literature, and there is no unified framework to understand the search mechanisms of different algorithms. Therefore, this paper attempts to analyse some similarities and differences among different algorithms and then presents a generalized evolutionary metaheuristic (GEM) in an attempt to unify some of the existing algorithms. After a brief discussion of some insights into nature-inspired algorithms and some open problems, we propose a generalized evolutionary metaheuristic algorithm to unify more than 20 different algorithms so as to understand their main steps and search mechanisms. We then test the unified GEM using 15 test benchmarks to validate its performance. Finally, further research topics are briefly discussed.

关键词： Algorithm derivative-free algorithm evolutionary computation metaheuristic nature-inspired computing swarm intelligence optimization

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial Special Issue on evolutionary Computer Vision

引用

IEEE TRANSACTIONS ON evolutionary computation 2023年第1期27卷 2-4页

作者： Olague, Gustavo Koppen, Mario Cordon, Oscar Ctr Invest Cient & Educ Super Ensenada Dept Comp Sci Appl Phys Div EvoVis Lab Ensenada 22860 Mexico Kyushu Inst Technol Dept Comp Sci & Networks Fukuoka 8208502 Japan Univ Granada Andalusian Res Inst Data Sci & Artificial Intelli Granada 18071 Spain Univ Granada Dept Comp Sci & Artificial Intelligence Granada 18071 Spain

evolutionary Computer Vision (ECV) is at the intersection of two major research fields of artificial intelligence: 1) computer vision (CV) and 2) evolutionary computation (EC). This special issue brings an overview of state-of-the-art contributions to the latest research and development in the discipline. CV includes methods for acquiring, processing, analyzing, and understanding images. The aim is to design computational models of human and animal perception. ECV is an interdisciplinary research area where analytical methods combined with powerful stochastic optimization and metaheuristic approaches produced human-competitive results. From an engineering standpoint, ECV aims to design software and hardware solutions useful for solving challenging CV problems. From a scientific viewpoint, the goal is to enhance our current understanding of visual processing in nature and replicate this within a seeing machine. ECV is a well-established research discipline as evolutionary algorithms are more efficient than classical optimization approaches for the discontinuous, nondifferentiable, multimodal, and noisy search, optimization, and learning problems arising in many CV tasks. EC has also demonstrated its ability as a robust approach to cope with the fundamental steps of image processing, image analysis, and image understanding included in the CV pipeline (e.g., restoration, segmentation, registration, classification, reconstruction, or tracking).

关键词： Special issues and sections evolutionary computation Computer vision Stochastic processes Research and development Search problems

来源：评论

学校读者我要写书评

暂无评论

evolutionary Trajectory Optimization for Suborbital Spaceplane by Combining Direct and Inverse Trajectory Design Approach

Evolutionary Trajectory Optimization for Suborbital Spacepla...

引用

Asia-Pacific International Symposium on Aerospace Technology (APISAT)

作者： Murakami, Masaaki Fujikawa, Takahiro Yonemoto, Koichi Tokyo Univ Sci Chiba Japan

ISBN: (纸本)9789819740123;9789819740109;9789819740093

This paper proposes evolutionary trajectory optimization methodology for suborbital spaceplanes that combines direct and inverse trajectory design approach. Guidance of suborbital spaceplane has attracted attention as a method to generate and update new trajectories in flight, and trajectory optimization by evolutionary computation enables global search. The trajectory of a spaceplane is subject to several strict constraints including flight path, aerodynamic loads, and longitudinal trim, making it difficult to find feasible solutions. The proposed methodology focuses on the dynamics of the trajectory, and flight constraints are handled efficiently. In the region where the angle of attack constraint changes drastically from transonic to hypersonic due to longitudinal trim constraints, the time history control input is directly designed to obtain the trajectory. In the end of the flight after deceleration to subsonic speed, the inverse designmethod is applied to satisfy the path constraints. The proposed method was validated by simulation, and it was confirmed that a diversity of solutions that fully satisfy the constraints can be obtained with a relatively small number of generations and individuals.

关键词： Real-time trajectory generation evolutionary computation Quaternion Spaceplane

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimization in Asynchronous Environments: An evolutionary Game Theory Approach 32

Multi-Objective Optimization in Asynchronous Environments: A...

引用

32nd International Conference on Modeling, Analysis and Simulation of Computer and Telecommunication Systems

作者： Jarosz, Pawel Marszalek, Adam Cracow Univ Technol Fac Comp Sci & Telecommun Krakow Poland

ISBN: (纸本)9798331531317;9798331531300

This paper presents an innovative approach to solving complex multi-objective optimization problems through an asynchronous and distributed evolutionary game theory method. The proposed algorithm, an extension of the IMGAMO algorithm, optimizes individual criteria separately at varying computational speeds, thus significantly enhancing computational efficiency and adaptability. This unique structure enables independent criterion optimization, catering to real-world applications where different objectives demand varying computational resources. The algorithm's effectiveness is validated against traditional synchronous evolutionary multi-objective optimization algorithms, showing superior performance in handling diverse, real-world problems efficiently. The results underline the potential of the asynchronous approach in providing high-quality Pareto fronts, thus offering robust solutions for complex optimization challenges.

关键词： Multiobjective optimization Pareto optimization evolutionary computation Asynchronous computation

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Differential Evolution Algorithm with Levy Flight 18th

Reinforcement Learning-Based Differential Evolution Algorith...

引用

18th International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA)

作者： Liu, Xiaoyu Zhang, Qingke Xi, Hongtong Zhang, Huixia Gao, Shuang Zhang, Huaxiang Shandong Normal Univ Sch Informat Sci & Engn Jinan 250358 Peoples R China

ISBN: (纸本)9789819722716;9789819722723

In this paper, a reinforcement learning-based differential evolution algorithm with levy flight strategy (RLLDE) for solving optimization problems is proposed. It introduces a novel mutation mode considering search directions is proposed firstly. Secondly, a levy flight strategy is employed to enhance the exploration capability of Differential Evolution (DE). Lastly, the Q-learning method from reinforcement learning is introduced to establish a switching mechanism between two different updating modes during the mutation stage. These strategies effectively improve the algorithm's convergence speed and accuracy. RLLDE is analyzed on CEC 2017 benchmark functions to validate its optimization performance. Compared to five basic DE and eight efficient optimizers, the experimental results demonstrate that the algorithm exhibits efficient and effective performance in solving optimization problems.

关键词： evolutionary computation Differential evolution Reinforcement learning Levy flight

来源：评论

学校读者我要写书评

暂无评论

Heuristic Initialization and Knowledge-based Mutation for Large-Scale Multi-Objective 0-1 Knapsack Problems

Heuristic Initialization and Knowledge-based Mutation for La...

引用

Genetic and evolutionary computation Conference (GECCO)

作者： Gong, Cheng Nan, Yang Pang, Lie Meng Zhang, Qingfu Ishibuchi, Hisao City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Southern Univ Sci & Technol Shenzhen 518055 Peoples R China City Univ Hong Kong Shenzhen Res Inst Shenzhen Peoples R China

ISBN: (纸本)9798400704949

Recently, there has been a growing interest in large-scale multi-objective optimization problems within the evolutionary multiobjective optimization (EMO) community. These problems involve hundreds or thousands of decision variables and multiple conflicting objectives, which pose significant challenges for conventional EMO algorithms (EMOAs). It is generally believed that EMOAs have difficulty in efficiently finding good non-dominated solutions as the number of decision variables increases. To address this issue, in this paper, we propose a novel method that incorporates heuristic initialization and knowledge-based mutation into EMOAs for solving large-scale multi-objective 0-1 knapsack problems. Various large-scale multi-objective 0-1 knapsack problems with an arbitrary number of constraints are generated as test problems to evaluate the effectiveness of the proposed method. Experimental results show that the proposed novel initialization and mutation method significantly improves the performance of the original EMOAs in terms of both the convergence speed in early generations and the quality of the final population.

关键词： Multi-objective optimization large-scale combinatorial optimization evolutionary computation EMO algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution

Learning Descriptors for Novelty-Search Based Instance Gener...

引用

Genetic and evolutionary computation Conference (GECCO)

作者： Marrero, Alejandro Segredo, Eduardo Leon, Coromoto Hart, Emma Univ La Laguna San Cristobal La Laguna Spain Edinburgh Napier Univ Edinburgh Midlothian Scotland

ISBN: (纸本)9798400704949

The ability to generate example instances from a domain is important in order to benchmark algorithms and to generate data that covers an instance-space in order to train machine-learning models for algorithm selection. Quality-Diversity (QD) algorithms have recently been shown to be effective in generating diverse and discriminatory instances with respect to a portfolio of solvers in various combinatorial optimisation domains. However these methods all rely on defining a descriptor which defines the space in which the algorithm searches for diversity: this is usually done manually defining a vector of features relevant to the domain. As this is a limiting factor in the use of QD methods, we propose a meta-QD algorithm which uses an evolutionary algorithm to search for a non-linear 2D projection of an original feature-space such that applying novelty-search method in this space to generate instances improves the coverage of the instance-space. We demonstrate the effectiveness of the approach by generating instances from the Knapsack domain, showing the meta-QD approach both generates instances in regions of an instance-space not covered by other methods, and also produces significantly more instances.

关键词： Instance generation instance-space analysis knapsack problem novelty search evolutionary computation neural-network

来源：评论

学校读者我要写书评

暂无评论

Understanding the Importance of evolutionary Search in Automated Heuristic Design with Large Language Models 18th

Understanding the Importance of Evolutionary Search in Autom...

引用

18th International Conference on Parallel Problem Solving from Nature (PPSN)

作者： Zhang, Rui Liu, Fei Lin, Xi Wang, Zhenkun Lu, Zhichao Zhang, Qingfu City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China Southern Univ Sci & Technol Sch Syst Design & Intelligent Mfg Shenzhen Peoples R China

ISBN: (纸本)9783031700675;9783031700682

Automated heuristic design (AHD) has gained considerable attention for its potential to automate the development of effective heuristics. The recent advent of large language models (LLMs) has paved a new avenue for AHD, with initial efforts focusing on framing AHD as an evolutionary program search (EPS) problem. However, inconsistent benchmark settings, inadequate baselines, and a lack of detailed component analysis have left the necessity of integrating LLMs with search strategies and the true progress achieved by existing LLM-based EPS methods to be inadequately justified. This work seeks to fulfill these research queries by conducting a large-scale benchmark comprising four LLM-based EPS methods and four AHD problems across nine LLMs and five independent runs. Our extensive experiments yield meaningful insights, providing empirical grounding for the importance of evolutionary search in LLM-based AHD approaches, while also contributing to the advancement of future EPS algorithmic development. To foster accessibility and reproducibility, we have fully open-sourced our benchmark and corresponding results.

关键词： Automated heuristic design evolutionary program search large language model evolutionary computation

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：