AppGP: An alternative structural representation for GP

Nicholas Freitag McPhee; Nick Hopper

doi:10.1109/CEC.1999.782643

AppGP: An alternative structural representation for GP

Nicholas Freitag McPhee
, Nick Hopper

Computer Science and Engineering

Research output: Contribution to conference › Paper › peer-review

2 Scopus citations

Abstract

It has been shown that standard genetic programming using standard subtree crossover is prone to a form of structural convergence which makes it extremely difficult to make changes near the root, occasionally causing runs to become trapped in local maxima. Based on these structural limitations we propose a different tree representation, AppGP, which we hope will avoid this problem in some cases. In this paper, we describe this representation, and compare its performance to the performance of standard GP on a suite of test problems. We find that on all of the test problems, AppGP does no worse than standard GP, and in several it does considerably better, suggesting that the representation warrants further study.

Original language	English (US)
Pages	1377-1383
Number of pages	7
DOIs	https://doi.org/10.1109/CEC.1999.782643
State	Published - 1999
Event	1999 Congress on Evolutionary Computation, CEC 1999 - Washington, DC, United States Duration: Jul 6 1999 → Jul 9 1999

Other

Other	1999 Congress on Evolutionary Computation, CEC 1999
Country/Territory	United States
City	Washington, DC
Period	7/6/99 → 7/9/99

Publisher link

10.1109/CEC.1999.782643

Find It

Find It at U of M Libraries

Cite this

@conference{72217590655b41bb8d3d23dca8821309,

title = "AppGP: An alternative structural representation for GP",

abstract = "It has been shown that standard genetic programming using standard subtree crossover is prone to a form of structural convergence which makes it extremely difficult to make changes near the root, occasionally causing runs to become trapped in local maxima. Based on these structural limitations we propose a different tree representation, AppGP, which we hope will avoid this problem in some cases. In this paper, we describe this representation, and compare its performance to the performance of standard GP on a suite of test problems. We find that on all of the test problems, AppGP does no worse than standard GP, and in several it does considerably better, suggesting that the representation warrants further study.",

author = "\{Freitag McPhee\}, Nicholas and Nick Hopper",

year = "1999",

doi = "10.1109/CEC.1999.782643",

language = "English (US)",

pages = "1377--1383",

note = "1999 Congress on Evolutionary Computation, CEC 1999 ; Conference date: 06-07-1999 Through 09-07-1999",

}

TY - CONF

T1 - AppGP

T2 - 1999 Congress on Evolutionary Computation, CEC 1999

AU - Freitag McPhee, Nicholas

AU - Hopper, Nick

PY - 1999

Y1 - 1999

N2 - It has been shown that standard genetic programming using standard subtree crossover is prone to a form of structural convergence which makes it extremely difficult to make changes near the root, occasionally causing runs to become trapped in local maxima. Based on these structural limitations we propose a different tree representation, AppGP, which we hope will avoid this problem in some cases. In this paper, we describe this representation, and compare its performance to the performance of standard GP on a suite of test problems. We find that on all of the test problems, AppGP does no worse than standard GP, and in several it does considerably better, suggesting that the representation warrants further study.

AB - It has been shown that standard genetic programming using standard subtree crossover is prone to a form of structural convergence which makes it extremely difficult to make changes near the root, occasionally causing runs to become trapped in local maxima. Based on these structural limitations we propose a different tree representation, AppGP, which we hope will avoid this problem in some cases. In this paper, we describe this representation, and compare its performance to the performance of standard GP on a suite of test problems. We find that on all of the test problems, AppGP does no worse than standard GP, and in several it does considerably better, suggesting that the representation warrants further study.

UR - https://www.scopus.com/pages/publications/70349939092

UR - https://www.scopus.com/pages/publications/70349939092#tab=citedBy

U2 - 10.1109/CEC.1999.782643

DO - 10.1109/CEC.1999.782643

M3 - Paper

AN - SCOPUS:70349939092

SP - 1377

EP - 1383

Y2 - 6 July 1999 through 9 July 1999

ER -

AppGP: An alternative structural representation for GP

Abstract

Other

Publisher link

Find It

Other files and links

Fingerprint

Cite this