Hardware accelerators for Cartesian genetic programming

被引：0
|
作者：
Vasicek, Zdenek [1 ]
Sekanina, Lukas [1 ]
机构：
[1] Brno Univ Technol, Fac Informat Technol, Bozetechova 2, Brno 612664, Czech Republic
来源：
GENETIC PROGRAMMING, PROCEEDINGS | 2008年 / 4971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：
A new class of FPGA-based accelerators is presented for Cartesian Genetic Programming (CGP). The accelerators contain a genetic engine which is reused in all applications. Candidate programs (circuits) are evaluated using application-specific virtual reconfigurable circuit (VRC) and fitness unit. Two types of VRCs are proposed. The first one is devoted for symbolic regression problems over the fixed point representation. The second one is designed for evolution of logic circuits. In both cases a significant speedup of evolution (30-40 times) was obtained in comparison with a highly optimized software implementation of CGP. This speedup can be increased by creating multiple fitness units.
引用
收藏
页码：230 / +
页数：2
相关论文
共 50 条
  • [31] Cartesian genetic programming: its status and future
    Miller, Julian Francis
    GENETIC PROGRAMMING AND EVOLVABLE MACHINES, 2020, 21 (1-2) : 129 - 168
  • [32] Improving Image Filters with Cartesian Genetic Programming
    Biau, Julien
    Wilson, Dennis
    Cussat-Blanc, Sylvain
    Luga, Herve
    PROCEEDINGS OF THE 13TH INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL INTELLIGENCE (IJCCI), 2021, : 17 - 27
  • [33] FMCGP: frameshift mutation cartesian genetic programming
    Fang, Wei
    Gu, Mindan
    COMPLEX & INTELLIGENT SYSTEMS, 2021, 7 (03) : 1195 - 1206
  • [34] Cartesian genetic programming: its status and future
    Julian Francis Miller
    Genetic Programming and Evolvable Machines, 2020, 21 : 129 - 168
  • [35] Parametrizing Cartesian Genetic Programming: An Empirical Study
    Kaufmann, Paul
    Kalkreuth, Roman
    KI 2017: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2017, 10505 : 316 - 322
  • [36] Evofficient: Reproducing a Cartesian Genetic Programming Method
    Wendlinger, Lorenz
    Stier, Julian
    Granitzer, Michael
    GENETIC PROGRAMMING, EUROGP 2021, 2021, 12691 : 162 - 178
  • [37] Evolution and acquisition of modules in Cartesian Genetic Programming
    Walker, JA
    Miller, JF
    GENETIC PROGRAMMING, PROCEEDINGS, 2004, 3003 : 187 - 197
  • [38] Self Modifying Cartesian Genetic Programming: Parity
    Harding, S.
    Miller, J. F.
    Banzhaf, W.
    2009 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-5, 2009, : 285 - +
  • [39] A New Subgraph Crossover for Cartesian Genetic Programming
    Kalkreuth, Roman
    Rudolph, Gunter
    Droschinsky, Andre
    GENETIC PROGRAMMING, EUROGP 2017, 2017, 10196 : 294 - 310
  • [40] A Comparative Study on Crossover in Cartesian Genetic Programming
    Husa, Jakub
    Kalkreuth, Roman
    GENETIC PROGRAMMING (EUROGP 2018), 2018, 10781 : 203 - 219
12345