Genetically evolved trees representing ensembles

被引:0
|
作者
Johansson, Ulf [1 ]
Lofstrom, Tuve
Konig, Rikard
Niklasson, Lars
机构
[1] Univ Boras, Sch Business & Informat, Boras, Sweden
[2] Univ Skovde, Sch Humanities & Informat, Skovde, Sweden
来源
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING - ICAISC 2006, PROCEEDINGS | 2006年 / 4029卷
关键词
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
We have recently proposed a novel algorithm for ensemble creation called GEMS (Genetic Ensemble Member Selection). GEMS first trains a fixed number of neural networks (here twenty) and then uses genetic programming to combine these networks into an ensemble. The use of genetic programming makes it possible for GEMS to not only consider ensembles of different sizes, but also to use ensembles as intermediate building blocks. In this paper, which is the first extensive study of GEMS, the representation language is extended to include tests partitioning the data, further increasing flexibility. In addition, several micro techniques are applied to reduce overfitting, which appears to be the main problem for this powerful algorithm. The experiments show that GEMS, when evaluated on 15 publicly available data sets, obtains very high accuracy, clearly outperforming both straightforward ensemble designs and standard decision tree algorithms.
引用
收藏
页码:613 / 622
页数:10
相关论文
共 50 条
  • [31] Representing Directed Trees as Straight Skeletons
    Aichholzer, Oswin
    Biedl, Therese
    Hackl, Thomas
    Held, Martin
    Huber, Stefan
    Palfrader, Peter
    Vogtenhuber, Birgit
    GRAPH DRAWING AND NETWORK VISUALIZATION, GD 2015, 2015, 9411 : 335 - 347
  • [32] Representing dynamic binary trees succinctly
    Munro, JI
    Raman, V
    Storm, AJ
    PROCEEDINGS OF THE TWELFTH ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS, 2001, : 529 - 536
  • [33] Beyond Representing Orthology Relations by Trees
    K. T. Huber
    G. E. Scholz
    Algorithmica, 2018, 80 : 73 - 103
  • [34] Beyond Representing Orthology Relations by Trees
    Huber, K. T.
    Scholz, G. E.
    ALGORITHMICA, 2018, 80 (01) : 73 - 103
  • [35] Representing canonical models as probability trees
    del Sagrado, J
    Salmerón, A
    CURRENT TOPICS IN ARTIFICIAL INTELLIGENCE, 2004, 3040 : 478 - 487
  • [36] Genetically modified forest trees
    Burdon, RD
    INTERNATIONAL FORESTRY REVIEW, 2003, 5 (01) : 58 - 64
  • [37] Object recognition with genetically evolved dynamic link structure
    Li, B
    INTERNATIONAL CONFERENCE ON IMAGING SCIENCE, SYSTEMS, AND TECHNOLOGY, PROCEEDINGS, 1999, : 1 - 5
  • [38] Neural network with genetically evolved algorithms for stocks prediction
    Phua, PKH
    Ming, DH
    Lin, WD
    ASIA-PACIFIC JOURNAL OF OPERATIONAL RESEARCH, 2001, 18 (01) : 103 - 107
  • [39] An Explainable Classifier based on Genetically Evolved Graph Structures
    Bertini Junior, Joao Roberto
    Cano, Alberto
    2022 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2022,
  • [40] Genetically evolved transformations for rescaling online handwritten characters
    Deepu, V
    Madhvanath, S
    Proceedings of the IEEE INDICON 2004, 2004, : 262 - 265