Recurrent Cartesian Genetic Programming

被引：0
|
作者：
Turner, Andrew James [1 ]
Miller, Julian Francis [1 ]
机构：
[1] Univ York, York YO10 5DD, N Yorkshire, England
来源：
PARALLEL PROBLEM SOLVING FROM NATURE - PPSN XIII | 2014年 / 8672卷
关键词：
NEUTRALITY;
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：
This paper formally introduces Recurrent Cartesian Genetic Programming (RCGP), an extension to Cartesian Genetic Programming (CGP) which allows recurrent connections. The presence of recurrent connections enables RCGP to be successfully applied to partially observable tasks. It is found that RCGP significantly outperforms CGP on two partially observable tasks: artificial ant and sunspot prediction. The paper also introduces a new parameter, recurrent connection probability, which biases the number of recurrent connections created via mutation. Suitable choices of this parameter significantly improve the effectiveness of RCGP.
引用
收藏
页码：476 / 486
页数：11
相关论文
共 50 条
  • [1] Recurrent Cartesian Genetic Programming of Artificial Neural Networks
    Turner, Andrew James
    Miller, Julian Francis
    [J]. GENETIC PROGRAMMING AND EVOLVABLE MACHINES, 2017, 18 (02) : 185 - 212
  • [2] Recurrent Cartesian Genetic Programming of Artificial Neural Networks
    Andrew James Turner
    Julian Francis Miller
    [J]. Genetic Programming and Evolvable Machines, 2017, 18 : 185 - 212
  • [3] Cartesian genetic programming
    Miller, JF
    Thomson, P
    [J]. GENETIC PROGRAMMING, PROCEEDINGS, 2000, 1802 : 121 - 132
  • [4] A comparison of Cartesian Genetic Programming and Linear Genetic Programming
    Wilson, Garnett
    Banzhaf, Wolfgang
    [J]. GENETIC PROGRAMMING, PROCEEDINGS, 2008, 4971 : 182 - 193
  • [5] On the Parameterization of Cartesian Genetic Programming
    Kaufmann, Paul
    Kalkreuth, Roman
    [J]. 2020 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), 2020,
  • [6] Complexity and Cartesian Genetic Programming
    Woodward, JR
    [J]. GENETIC PROGRAMMING, PROCEEDINGS, 2006, 3905 : 260 - 269
  • [7] Hardware accelerators for Cartesian genetic programming
    Vasicek, Zdenek
    Sekanina, Lukas
    [J]. GENETIC PROGRAMMING, PROCEEDINGS, 2008, 4971 : 230 - +
  • [8] Asynchronous Parallel Cartesian Genetic Programming
    Harter, Adam
    Tauritz, Daniel R.
    Siever, William M.
    [J]. PROCEEDINGS OF THE 2017 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION (GECCO'17 COMPANION), 2017, : 1820 - 1824
  • [9] A New Crossover Technique for Cartesian Genetic Programming Genetic Programming Track
    Clegg, Janet
    Walker, James Alfred
    Miller, Julian Francis
    [J]. GECCO 2007: GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, VOL 1 AND 2, 2007, : 1580 - 1587
  • [10] Multitask Evolution with Cartesian Genetic Programming
    Scott, Eric O.
    De Jong, Kenneth A.
    [J]. PROCEEDINGS OF THE 2017 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION (GECCO'17 COMPANION), 2017, : 255 - 256
12345