Relating training instances to automatic design of algorithms for bin packing via features

Relating training instances to automatic design of algorithms for bin packing via features
复制标题

通过特征将训练实例与装箱算法的自动设计联系起来

DOI:
10.1145/3205651.3205748
复制
发表时间:
2018
期刊:
--
影响因子:
--
通讯作者:
Brownlee A
Brownlee A
中科院分区:
--
文献类型:
--
作者:
Brownlee A

文献摘要

参考文献

相似文献

算法自动设计 (ADA) 将算法选择和设计视为机器学习问题,以问题实例作为训练数据。然而,本文揭示了,与分类和回归一样,对于 ADA 而言,并非所有训练集都具有同等价值。我们将用于装箱的遗传编程 ADA 应用于几个新的和现有的基准集。使用具有窄分布特征的集合进行训练会产生高度专业化的算法,而具有广泛分布特征的集合会产生非常通用的算法。某些特征的差异与训练策略的通用性有很强的相关性。
Automatic Design of Algorithms (ADA) treats algorithm choice and design as a machine learning problem, with problem instances as training data. However, this paper reveals that, as with classification and regression, for ADA not all training sets are equally valuable.We apply genetic programming ADA for bin packing to several new and existing benchmark sets. Using sets with narrowly-distributed features for training results in highly specialised algorithms, whereas those with well-spread features result in very general algorithms. Variance in certain features has a strong correlation with the generality of the trained policies.
DOI: --
发表时间: 2009
期刊: Encyclopedia of Data Warehousing and Mining
影响因子: --
作者:
A. Freitas;G. Pappa
通讯作者: G. Pappa
DOI: --
发表时间: 2013
期刊: European Conference on Genetic Programming
影响因子: --
作者:
Libin Hong;J. Woodward;Jingpeng Li;E. Özcan
通讯作者: E. Özcan
使用数据挖掘预测图着色问题的元启发式性能
DOI: --
发表时间: 2013
期刊: Hybrid Metaheuristics
影响因子: --
作者:
K. Smith‐Miles;Brendan Wreford;Leo Lopes;N. Insani
通讯作者: N. Insani
通过遗传编程改进装箱启发法
DOI: --
发表时间: 2006
期刊: Parallel Problem Solving from Nature
影响因子: --
作者:
E. Burke;Matthew R. Hyde;G. Kendall
通讯作者: G. Kendall
基于矩阵分解的基准集分析:HyFlex 案例研究
DOI: 10.1007/978-3-319-68759-9_16
发表时间: 2017
期刊: Turkish Journal of Computer and Mathematics Education (TURCOMAT)
影响因子: --
作者:
Mustafa Misir
通讯作者: Mustafa Misir