检索结果-内蒙古大学图书馆

Active learning and data manipulation techniques for generating training examples in meta-learning

NEUROCOMPUTING 2016年 194卷 45-55页

作者： Sousa, Arthur F. M. Prudencio, Ricardo B. C. Ludermir, Teresa B. Soares, Carlos Univ Fed Pernambuco Ctr Informat Recife PE Brazil Univ Porto Fac Engn INESC TEC Rua Campo Alegre 823 P-4100 Oporto Portugal

algorithm selection is an important task in different domains of knowledge. Meta-learning treats this task by adopting a supervised learning strategy. Training examples in meta-learning (called meta examples) are generated from experiments performed with a pool of candidate algorithms in a number of problems, usually collected from data repositories or synthetically generated. A meta-learner is then applied to acquire knowledge relating features of the problems and the best algorithms in terms of performance. In this paper, we address an important aspect in meta-learning which is to produce a significant number of relevant meta-examples. Generating a high quality set of meta-examples can be difficult due to the low availability of real datasets in some domains and the high computational cost of labelling the meta-examples. In the current work, we focus on the generation of meta-examples for meta-learning by combining: (1) a promising approach to generate new datasets (called datasetoids) by manipulating existing ones;and (2) active learning methods to select the most relevant datasets previously generated. The datasetoids approach is adopted to augment the number of useful problem instances for meta-example construction. However not all generated problems are equally relevant. Active meta-learning then arises to select only the most informative instances to be labelled. Experiments were performed in different scenarios, algorithms for meta-learning and strategies to select datasets. Our experiments revealed that it is possible to reduce the computational cost of generating meta-examples, while maintaining a good meta-learning performance. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Meta-learning algorithm selection Active learning

来源：评论

学校读者我要写书评

暂无评论

A generic method to compose an algorithm portfolio with a problem set of unknown distribution

引用

MEMETIC COMPUTING 2022年第3期14卷 287-304页

作者： Liu, Wenwen Yuen, Shiu Yin Sung, Chi Wan City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

As an individual algorithm rarely outperforms all kinds of optimization problems, algorithm portfolios are proposed to combine algorithms and take advantage of their strengths which fits well the prevalent theme of memetic computing. When there are many algorithms to choose from, the possibilities of algorithm combinations are numerous. Therefore, composing an algorithm portfolio which performs well for a given problem class is essential. In this paper, based on a problem set drawn from any unknown problem class according to an unknown probability distribution, we propose a general method to automatically accomplish portfolio construction. The problem set is used as training data for our method to learn an algorithm portfolio suitable for solving the underlying problem class. To construct the portfolio, algorithms are chosen and added one by one. We first find the best-performing algorithm based on its average rank of solving the training problem set. Its most complementary algorithm is then selected by applying the Pearson correlation coefficient of fitness values at the first hitting time. The method iterates to compose the portfolio with more and more algorithms until there is no more improvement. The experimental results indicate the effectiveness of this approach to select well-cooperated algorithms, and the composed portfolio is shown to have the best rank compared to individual algorithms, elite portfolios and comparison algorithms.

关键词： algorithm portfolio composition algorithm selection Black box optimization problem

来源：评论

学校读者我要写书评

暂无评论

A survey of fitness landscape analysis for optimization

引用

NEUROCOMPUTING 2022年 503卷 129-139页

作者： Zou, Feng Chen, Debao Liu, Hui Cao, Siyu Ji, Xuying Zhang, Yan Huaibei Normal Univ Sch Phys & Elect Informat Huaibei 235000 Peoples R China Huaibei Normal Univ Sch Comp Sci & Technol Huaibei 235000 Peoples R China

Over past few decades, as a powerful analytical tool to characterize the fitness landscape of a problem, fitness landscape analysis (FLA) has been widely concerned and utilized for all kinds of optimization areas. Since its introduction by Sewell Wright in 1932, FLA has attracted more and more attention of researchers for its research significance and application value such as an intuitive understanding features of complex optimization problems, explaining evolutionary algorithm behavior, assessing performances of algorithms, and guiding selections and/or configures of algorithms. This paper attempts to give an overview of fitness landscape analysis and its typical application for optimization so far. We hope that this survey can help to understand features of complex optimization problems in depth and thus to improve the certain algorithm performance of for a given optimization problem.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Survey Fitness landscape Landscape analysis Heuristic algorithms algorithm selection

来源：评论

学校读者我要写书评

暂无评论

Adaptive recommendation model using meta-learning for population-based algorithms

引用

INFORMATION SCIENCES 2019年 476卷 192-210页

作者： Chu, Xianghua Cai, Fulin Cui, Can Hu, Mengqi Li, Li Qin, Quande Shenzhen Univ Coll Management Shenzhen Peoples R China Shenzhen Univ Inst Big Data Intelligent Management & Decis Shenzhen Peoples R China Arizona State Univ Sch Comp Informat Decis Syst Engn Tempe AZ 85287 USA Univ Illinois Dept Mech & Ind Engn Chicago IL USA

To efficiently solve complex optimization problems, numerous population-based meta heuristics and extensions have been developed. However, the performances of the algorithms vary depending on the problems. In this research, we propose an Adaptive Recommendation Model (ARM) using meta-learning to identify appropriate problem-dependent population-based algorithm. In ARM, the algorithms are adaptively selected by mapping the problem characteristics to the algorithm performance. Since the meta-features extracted and meta-learner adopted would significantly affect the system performance, 18 meta-features including statistical, geometrical and landscape features are extracted to characterize optimization problem spaces. Both instance-based and model-based learners are investigated. Two performance metrics, Spearman's rank correlation coefficient and success rate are used to evaluate the accuracy of optimizer's ranking prediction and the precision of the best optimizer recommendation. The proposed ARM is compared against population-based algorithms with distinct search capabilities such as PSO variants, non-PSO population-based optimizers, hyper-heuristics and ensemble methods. Benchmark functions and real-world problems with various properties are adopted in the experiments. Experimental results reveal the extendibility and effectiveness of ARM on the diverse tested problems in terms of solution accuracy, ranking and success rate. (C) 2018 Elsevier Inc. All rights reserved.

关键词： Global optimization algorithm selection Meta-learning Population-based algorithm Recommendation system

来源：评论

学校读者我要写书评

暂无评论

Towards objective measures of algorithm performance across instance space

引用

COMPUTERS & OPERATIONS RESEARCH 2014年第May期45卷 12-24页

作者： Smith-Miles, Kate Baatar, Davaatseren Wreford, Brendan Lewis, Rhyd Monash Univ Sch Math Sci Clayton Vic 3800 Australia Cardiff Univ Sch Math Cardiff CF10 3AX S Glam Wales

This paper tackles the difficult but important task of objective algorithm performance assessment for optimization. Rather than reporting average performance of algorithms across a set of chosen instances, which may bias conclusions, we propose a methodology to enable the strengths and weaknesses of different optimization algorithms to be compared across a broader instance space. The results reported in a recent Computers and Operations Research paper comparing the performance of graph coloring heuristics are revisited with this new methodology to demonstrate (i) how pockets of the instance space can be found where algorithm performance varies significantly from the average performance of an algorithm;(ii) how the properties of the instances can be used to predict algorithm performance on previously unseen instances with high accuracy;and (iii) how the relative strengths and weaknesses of each algorithm can be visualized and measured objectively. (C) 2013 Elsevier Ltd. All rights reserved.

关键词： Comparative analysis Heuristics Graph coloring algorithm selection Performance prediction

来源：评论

学校读者我要写书评

暂无评论

SUNNY-CP and the MiniZinc challenge

引用

THEORY AND PRACTICE OF LOGIC PROGRAMMING 2018年第1期18卷 81-96页

作者： Amadini, Roberto Gabbrielli, Maurizio Mauro, Jacopo Univ Melbourne Dept Comp & Informat Syst Melbourne Vic Australia Univ Bologna DISI Bologna Italy FOCUS Res Team Bologna Italy Univ Oslo Dept Informat Oslo Norway

In Constraint Programming, a portfolio solver combines a variety of different constraint solvers for solving a given problem. This fairly recent approach enables to significantly boost the performance of single solvers, especially when multicore architectures are exploited. In this work, we give a brief overview of the portfolio solver sunny-cp, and we discuss its performance in the MiniZinc Challenge-the annual international competition for Constraint Programming solvers-where it won two gold medals in 2015 and 2016.

关键词： Constraint Programming algorithm selection Algorith Portfolios MiniZinc

来源：评论

学校读者我要写书评

暂无评论

Learning a Confidence Measure for Optical Flow

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2013年第5期35卷 1107-1120页

作者： Mac Aodha, Oisin Humayun, Ahmad Pollefeys, Marc Brostow, Gabriel J. UCL Dept Comp Sci London WC1E 6BT England Georgia Inst Technol Sch Interact Comp Atlanta GA 30332 USA Swiss Fed Inst Technol Comp Vis & Geometry Lab Dept Comp Sci CH-8092 Zurich Switzerland

We present a supervised learning-based method to estimate a per-pixel confidence for optical flow vectors. Regions of low texture and pixels close to occlusion boundaries are known to be difficult for optical flow algorithms. Using a spatiotemporal feature vector, we estimate if a flow algorithm is likely to fail in a given region. Our method is not restricted to any specific class of flow algorithm and does not make any scene specific assumptions. By automatically learning this confidence, we can combine the output of several computed flow fields from different algorithms to select the best performing algorithm per pixel. Our optical flow confidence measure allows one to achieve better overall results by discarding the most troublesome pixels. We illustrate the effectiveness of our method on four different optical flow algorithms over a variety of real and synthetic sequences. For algorithm selection, we achieve the top overall results on a large test set, and at times even surpass the results of the best algorithm among the candidates.

关键词： Optical flow confidence measure Random Forest synthetic data algorithm selection

来源：评论

学校读者我要写书评

暂无评论

Fairness, Stability and Optimality of Adaptive Multiagent Systems: Interaction Through Resource Sharing

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2010年第3期7卷 427-439页

作者： Lee, Seokcheon Purdue Univ Sch Ind Engn W Lafayette IN 47907 USA

An argument for stability is derived for multiagent systems characterized by resource sharing and algorithm selection. These multiagent systems reflect the trends of modern information systems and the argument made here can serve as a guide to designing robust multiagent systems. The argument is that fairness leads to stability and consequently optimality. The fairness is allocating resources according to the utilities achievable by individual agents. On the other hand, unfairness arises when resources are allocated strictly equally or as reserved beforehand. The source of instability is identified as excess resources resulting from the unfairness. Since excess resources of some agents can be utilized by others, a system becomes vulnerable to instability due to the interactions from resource sharing. The fairness eliminates excess resources and agents become securing definite valuations of resources, as a result of utility-maximizing behaviors. As a consequence, the system reaches an optimal equilibrium voluntarily after any perturbation. Note to Practitioners-Multiagent system designers must understand the collective behavior resulting from the interactions between agents in order to build robust systems. For this purpose, there have been efforts to provide appropriate arguments of stability depending on the nature of system. For example, agent diversity was identified as a key to stabilizing computational ecosystem model and information sharing to supply chain networks. This paper drives an argument of stability for the multiagent systems characterized by resource sharing and algorithms selection. Individual systems are increasingly sharing resources and software systems are becoming capable of adapting to environmental changes through alternative algorithms. The argument is that fairness in such multiagent systems leads to stability and consequently optimality. However, despite of pursuing fairness, there can be diverse obstacles that give rise to unfairness. The

关键词： Adaptive multiagent systems algorithm selection fairness optimality resource sharing stability

来源：评论

学校读者我要写书评

暂无评论

3D meta-classification: A meta-learning approach for selecting 3D point-cloud classification algorithm

引用

INFORMATION SCIENCES 2024年 662卷

作者： Xu, Fan Chen, Jun Shi, Yizhou Ruan, Tianchen Wu, Qihui Zhang, Xiaofei Nanjing Univ Aeronaut & Astronaut Coll Elect & Informat Engn Nanjing 211106 Peoples R China

algorithm selection technology, aimed at choosing the most suitable algorithm for a given machine learning task, has achieved significant success in the domain of 2D vision. However, few studies have explored its application to the 3D point cloud domain. The rapid proliferation and development of 3D point cloud classification algorithms underscore the urgent need for exploration in selecting these algorithms. In this paper, we propose a novel meta -learningbased 3D classification approach, termed 3D meta -classification, to address this gap. The approach operates at both the base -level and meta -level phases. At the base level, candidate 3D classification algorithms constantly classify various 3D datasets, recording their classification performance as empirical knowledge. As for the meta -level phase, it specifically tailors the 3D meta -knowledge generator, 3D meta -feature extractor, and 3D meta -database constructor to establish the 3D meta -database, capturing the relationship between the 3D meta -features and empirical knowledge. Leveraging the 3D meta -database, the 3D classification meta -learner trains the meta -model and predicts suitable algorithms for new incoming 3D datasets. Extensive experiments are conducted to select the best -performing classification algorithm for specific 3D datasets from ModelNet40. The results demonstrate the effectiveness of the proposed 3D metaclassification model;the accuracies of one -from -two and one -from -three algorithm selection tasks reach over 98% and 80%, respectively.

关键词： Meta-learning 3D point-cloud classification algorithm selection 3D meta-features 3D classification meta-learner

来源：评论

学校读者我要写书评

暂无评论

Cognitive capabilities for the CAAI in cyber-physical production systems

引用

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 2021年第11-12期115卷 3513-3532页

作者： Strohschein, Jan Fischbach, Andreas Bunte, Andreas Faeskorn-Woyke, Heide Moriz, Natalia Bartz-Beielstein, Thomas TH Koln Inst Comp Sci Gummersbach Germany TH Koln Inst Data Sci Engn & Analyt Gummersbach Germany OWL Univ Appl Sci & Arts Inst Ind IT Lemgo Germany

This paper presents the cognitive module of the Cognitive Architecture for Artificial Intelligence (CAAI) in cyber-physical production systems (CPPS). The goal of this architecture is to reduce the implementation effort of artificial intelligence (AI) algorithms in CPPS. Declarative user goals and the provided algorithm-knowledge base allow the dynamic pipeline orchestration and configuration. A big data platform (BDP) instantiates the pipelines and monitors the CPPS performance for further evaluation through the cognitive module. Thus, the cognitive module is able to select feasible and robust configurations for process pipelines in varying use cases. Furthermore, it automatically adapts the models and algorithms based on model quality and resource consumption. The cognitive module also instantiates additional pipelines to evaluate algorithms from different classes on test functions. CAAI relies on well-defined interfaces to enable the integration of additional modules and reduce implementation effort. Finally, an implementation based on Docker, Kubernetes, and Kafka for the virtualization and orchestration of the individual modules and as messaging technology for module communication is used to evaluate a real-world use case.

关键词： Cognition Industry 4 0 Big data platform Machine learning CPPS Optimization algorithm selection Simulation

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：