Lecture 10

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: distribu/on as possible Non ­dominated Sor/ng GA: NSGA II •  Non ­dominated Sor/ng: –  Assign the fitness to each solu/on in the popula/on based on the non ­dominated sor/ng rank. •  Maintaining the diversity of the solu/ons: –  Assign each solu/on in the popula/on with a crowding distance value. •  Progress towards a well ­spread Pareto ­op/mal front: –  Preferring non ­dominated and low ­crowding distance solu/ons •  Elite ­preserva/on: μ+λ 2 2/11/14 Iden/fying the Non ­dominated Solu/ons in the Popula/on •  What is (are) the non ­dominated solu/ons? b c d e f a 5 e,f,c c 4 b 3 2 e f 1 c 0 0 e A simple Non ­dominated Sor/ng Algorithm •  Iden/fy the best non ­dominated set in the popula/on (use...
View Full Document

This document was uploaded on 02/28/2014 for the course CS 6776 at Memorial University.

Ask a homework question - tutors are online