WikiRNG
Rolled Version rolled

Parity benchmark

Parity problems are widely used as benchmark problems in genetic programming but inherited from the artificial neural network community. Parity is calculated by summing all the binary inputs and reporting if the sum is odd or even. This is considered difficult because:

  • a very simple artificial neural network cannot solve it, and
  • all inputs need to be considered and a change to any one of them changes the answer.
  • Foundations of Genetic Programming
BasicBottom 39%
33,469SP

Badges19 earned

  1. Notability?Obscure+12,927 SP
    Tagged as maybe not notable.
  1. Multiple IssuesNotable+5,495 SP
    Has the multiple issues box.
  2. Part of a SeriesNotable+3,604 SP
    Has a series sidebar.
  3. AnonymousNotable+3,128 SP
    Created by someone who wasn't logged in.
  4. Nice IDNotable+1,514 SP
    Page ID contains "69". ยท Page ID 1514696
  5. Stub-SizedNotable+1,199 SP
    Under 1,000 bytes. ยท 773 bytes
Basic13
rolled by Marovic