GEP: Symbolic Regression Problem


	Symbolic Regression Problem
Home News Author Q&A Tutorials Downloads GEP Biblio Contacts Visit Gepsoft

Symbolic regression with x⁴+x³+x²+x

Table 1
Parameters for the symbolic regression problem

Function set +,-,*,/

Terminal set a (x)

Number of fitness cases 10

Number of runs 100

Number of generations 50

Population size 30

Absolute error 0.01

Success rate 100%

Table 2 Comparison of GP and GEP on symbolic regression
	Exp	Gen	Pop	Fit. cases	Succ	R_z	F_z
GP	Koza [1]	51	500	20	0.35	11	5,610,000
GEP	Table 1	50	30	10	1	1	15,000

Conclusion:
In this case, GEP outperforms GP in 374 times (see How to evaluate the performance for details).

Download the executable

Bibliography:
1. Koza, J. R. (1992). Genetic Programming: On the Programming of Computers by Means of Natural Selection. Cambridge, MA: MIT Press.

Back

***

Last update: 23/July/2013