Better GP benchmarks: community survey results and proposals

被引：161

作者：

White, David R. ^{[1
]}

McDermott, James ^{[2
]}

Castelli, Mauro ^{[3
]}

Manzoni, Luca ^{[4
]}

Goldman, Brian W. ^{[5
]}

Kronberger, Gabriel ^{[6
]}

Jaskowski, Wojciech ^{[7
]}

O'Reilly, Una-May ^{[8
]}

Luke, Sean ^{[9
]}

机构：

[1] Univ Glasgow, Sch Comp Sci, Glasgow, Lanark, Scotland

[2] Univ Coll Dublin, Sch Business, Dublin 2, Ireland

[3] Univ Nova Lisboa, ISEGI, P-1200 Lisbon, Portugal

[4] Univ Milano Bicocca, Dipartimento Informat Sistemist & Comunicaz, Milan, Italy

[5] Michigan State Univ, BEACON Ctr Study Evolut Act, E Lansing, MI 48824 USA

[6] Univ Appl Sci Upper Austria, Linz, Austria

[7] Poznan Univ Tech, Inst Comp Sci, Poznan, Poland

[8] MIT, CSAIL, Cambridge, MA 02139 USA

[9] George Mason Univ, Dept Comp Sci, Fairfax, VA 22030 USA

来源：

GENETIC PROGRAMMING AND EVOLVABLE MACHINES | 2013年 / 14卷 / 01期

基金：

美国国家科学基金会;

关键词：

Genetic programming; Benchmarks; Community survey;

D O I：

10.1007/s10710-012-9177-2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present the results of a community survey regarding genetic programming benchmark practices. Analysis shows broad consensus that improvement is needed in problem selection and experimental rigor. While views expressed in the survey dissuade us from proposing a large-scale benchmark suite, we find community support for creating a "blacklist" of problems which are in common use but have important flaws, and whose use should therefore be discouraged. We propose a set of possible replacement problems.

引用

页码：3 / 29

页数：27

共 58 条

[1]

[Anonymous], 1994, Genetic programming II: Automatic discovery of reusable programs, DOI DOI 10.5555/183460

[2]

[Anonymous], 2010, P 12 INT ACM SIGPLAN, DOI DOI 10.1145/1836089.1836091

[3]

[Anonymous], 2012, P 29 INT C MACH LEAR

[4]

[Anonymous], HPL2001327

[5]

[Anonymous], 2003, Genetic programming IV: routine human-competitive machine intelligence

[6]

Bacardit J, 2006, GECCO 2006: GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, VOL 1 AND 2, P247

[7]

Barrero D.F, 2011, P C EV COMP

[8]

Christensen S., 2002, P EUROGP

[9] What Makes a Problem GP-Hard? Analysis of a Tunably Difficult Problem in Genetic Programming [J].

Jason M. Daida ;

Robert R. Bertram ;

Stephen A. Stanhope ;

Jonathan C. Khoo ;

Shahbaz A. Chaudhary ;

Omer A. Chaudhri ;

John A. II Polito .

Genetic Programming and Evolvable Machines, 2001, 2 (2) :165-191

[10] Evolving the Best Known Approximation to the Q Function [J].

Dao Ngoc Phong ;

Nguyen Xuan Hoai ;

McKay, R. I. ;

Siriteanu, Constantin ;

Nguyen Quang Uy ;

Park, Namyong .

PROCEEDINGS OF THE FOURTEENTH INTERNATIONAL CONFERENCE ON GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE, 2012, :807-812

← 1 2 3 4 5 6 →