[R-sig-eco] Function in Genetic Algorithms (SOLVED)

Daniel Patón d@p@ton@d @end|ng |rom gm@||@com
Wed Apr 1 20:47:44 CEST 2020


Dear all:

The GA package has a very different syntax than GAFIT. At work:

Luca Scrucca (2013) GA: A Package for Genetic Algorithms in R. Journal of Statistical Software. Vol 53 Issue 4

comes with an example with trees for curve fitting. 

In addition the algorithm works differently, since you do not explicit the data vectors in a separate function but in the input of the library. It requires instead a function in the abstract that defines the calculation. Another function to delimit the error. A different way of working for those of us who are used to simply using data matrices. Here the problem to be solved is defined by you. GAFIT is specially designed for curve fitting. GA for different kind of problems.  

I believe that these techniques are very useful in Ecology to adjust non-linear functions and require obviously less data than the Neural Networks I am more familiar with.

Regards
-- 
****************************************************************************
 Daniel Patón
 Numerical Ecology. Ecology Unit
 Department of Plant Biology, Ecology and Earth Sciences
 Faculty of Sciences. University of Extremadura
 Avda. Elvas s/n 06071 Badajoz (Spain)
 https://orcid.org/0000-0003-2500-3964
 https://cvn.fecyt.es/0000-0003-2500-3964
 http://unex.academia.edu/DanielPatonDominguez
 https://www.researchgate.net/profile/Daniel_Paton/
 http://sites.google.com/site/numericalecologyuex/home
 http://twitter.com/NumericalEcolo1
 https://www.youtube.com/channel/UCcDUrzoZQ5OID6uVxhcwBng



More information about the R-sig-ecology mailing list