Straight Line Programs: A new Linear Genetic Programming Approach

被引：8
作者：
Alonso, Cesar L. [1 ]
Puente, Jorge [1 ]
Montana, Jose Luis [2 ]
机构：
[1] Univ Oviedo, Ctr Inteligencia Artificial, Campus Viesques, Gijon 33271, Spain
[2] Univ Cantabria, Dept Mat Estadist Comput, Santander, Spain
来源：
20TH IEEE INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, VOL 2, PROCEEDINGS | 2008年
关键词：
D O I：
10.1109/ICTAI.2008.14
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Tree encodings of programs are well known for their representative power and are used very often in Genetic Programming. In this paper we experiment with a new data structure, named straight line program (sip), to represent computer programs. The main features of this structure are described and new recombination operators for GP related to slp's are introduced. Experiments have been performed on symbolic regression problems. Results are encouraging and suggest that the GP approach based on slp's consistently outperforms conventional GP based on tree structured representations.
引用
收藏
页码：517 / +
页数：2
相关论文
共 22 条
  • [1] [Anonymous], P 8 ANN C GEN EV COM
  • [2] Back T., 1996, EVOLUTIONARY ALGORIT
  • [3] BANZHAF W, 1993, P 5 INT C GEN ALG IG, P638
  • [4] BANZHAF W, 1998, M KAUFMANN SERIES AR
  • [5] ON COMPUTING THE DETERMINANT IN SMALL PARALLEL TIME USING A SMALL NUMBER OF PROCESSORS
    BERKOWITZ, SJ
    [J]. INFORMATION PROCESSING LETTERS, 1984, 18 (03) : 147 - 150
  • [6] Brameier MF, 2007, LINEAR GENETIC PROGR
  • [7] BURGUISSER P, 1997, COMPREHENSIVE STUDIE
  • [8] Model complexity control for regression using VC generalization bounds
    Cherkassky, V
    Shao, XH
    Mulier, FM
    Vapnik, VN
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (05): : 1075 - 1089
  • [9] Cramer N.L., 1985, Proceedings of the First International Conference on Genetic Algorithms and their Applications (ICGA'85), P183, DOI 10.4324/9781315799674-19
  • [10] Eiben AE, 2002, IEEE C EVOL COMPUTAT, P582, DOI 10.1109/CEC.2002.1006991
123