testing - What are some problems that genetic programming has solved successfully? -


i experimenting gp , wanted test problems have been solved gp. way, know genetic programming able provide solution works. also, shorter , simpler test cases better since i'm planning on running algorithm many times. thank you.

here's list of more common benchmark problems gp tested on. these used , descriptions of each should easy find google. thorough description of each, including suitable fitness functions , results can compare against see koza's first genetic programming book if can (the field has come on bit since then, they're not leading results, you're unlikely find more thorough descriptions).

boolean functions

  • even parity
  • odd parity
  • multiplexer (3-bit, 6-bit, 11-bit)
  • majority

symbolic regression

  • quartic polynomial
  • too many other functions mention

path finding

  • artificial ant (santa fe trail)
  • lawnmower
  • tartarus problem
  • circuit design
  • travelling salesman

control

  • cart centering
  • pole balancing

iterative/recursion

  • sorting
  • list reversion
  • fibonacci sequence
  • factorial

there's whole range of other problems gp has been tested on, here's few more, although these perhaps beyond you're looking @ moment:

  • game playing, including ms. pacman, othello, mario
  • classification problems (protein classification etc)
  • scheduling
  • financial trading
  • biped locomotion
  • antenna design

if you're looking few problems started with, see algorithm working , producing solutions, i'd suggest starting simple symbolic regression (where you're trying find mathematical formula), try 1 of simpler boolean problems such even-3-parity or 6-bit multiplexer. thing these problems can ramp difficulty changing formula you're trying find or increasing number of bits.


Comments

Popular posts from this blog

commonjs - How to write a typescript definition file for a node module that exports a function? -

openid - Okta: Failed to get authorization code through API call -

thorough guide for profiling racket code -