On the Existence of Feature Bundles and their Effect on Symbolic Regression Algorithms

被引：0
|
作者：
Neshatian, Kourosh [1 ]
Varn, Lucianne [1 ]
机构：
[1] Univ Canterbury, Dept Comp Sci & Software Engn, Christchurch, New Zealand
来源：
2017 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI) | 2017年
关键词：
symbolic regression; feature selection; genetic programming;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, we consider a special subset of the features in a regression learning problem that, while being relevant to the problem, its strict subsets do not show any sign of relevance. We discuss the presence of such subsets of features, which we call 'feature bundles', and examine the challenges they pose in feature selection and learning. We demonstrate the effect of these feature bundles on the performance of commonly-used symbolic regression algorithms.
引用
收藏
页码：2974 / 2981
页数：8
相关论文
共 50 条
  • [1] Feature Standardisation in Symbolic Regression
    Owen, Caitlin A.
    Dick, Grant
    Whigham, Peter A.
    [J]. AI 2018: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, 11320 : 565 - 576
  • [2] Feature Bundles and their Effect on the Performance of Tree-based Evolutionary Classification and Feature Selection Algorithms
    Neshatian, Kourosh
    Varn, Lucianne
    [J]. 2019 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2019, : 1612 - 1619
  • [3] Feature Standardisation and Coefficient Optimisation for Effective Symbolic Regression
    Dick, Grant
    Owen, Caitlin A.
    Whigham, Peter A.
    [J]. GECCO'20: PROCEEDINGS OF THE 2020 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2020, : 306 - 314
  • [4] Extremely Accurate Symbolic Regression for Large Feature Problems
    Korns, Michael F.
    [J]. GENETIC PROGRAMMING THEORY AND PRACTICE XII, 2015, : 109 - 131
  • [5] Benchmarking state-of-the-art symbolic regression algorithms
    Jan Žegklitz
    Petr Pošík
    [J]. Genetic Programming and Evolvable Machines, 2021, 22 : 5 - 33
  • [6] Benchmarking state-of-the-art symbolic regression algorithms
    Zegklitz, Jan
    Posik, Petr
    [J]. GENETIC PROGRAMMING AND EVOLVABLE MACHINES, 2021, 22 (01) : 5 - 33
  • [7] Symbolic regression as a feature engineering method for machine and deep learning regression tasks
    Shmuel, Assaf
    Glickman, Oren
    Lazebnik, Teddy
    [J]. MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2024, 5 (02):
  • [8] Automated Grammar-based Feature Selection in Symbolic Regression
    Ali, Muhammad Sarmad
    Kshirsagar, Meghana
    Naredo, Enrique
    Ryan, Conor
    [J]. PROCEEDINGS OF THE 2022 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'22), 2022, : 902 - 910
  • [9] Carousel Greedy Algorithms for Feature Selection in Linear Regression
    Wang, Jiaqi
    Golden, Bruce
    Cerrone, Carmine
    [J]. ALGORITHMS, 2023, 16 (09)
  • [10] Measuring Feature Importance of Symbolic Regression Models Using Partial Effects
    Imai Aldeia, Guilherme Seidyo
    de Franca, Fabricio Olivetti
    [J]. PROCEEDINGS OF THE 2021 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'21), 2021, : 750 - 758
12345