In this lecture, we reveal the basic architecture of the simple GA. We start with defining how to concretely implement chromosomes/genomes, genes, alleles, characters, and traits numerically within an Engineering Design Optimization context. We then move on to a general definition of multi-objective fitness (which we will return to in Unit 3 when we study multi-objective evolutionary algorithms) and show how fitness functions can be scaled not only to meet the assumptions on fitness functions but also to adjust selective pressure as desired. We close with a flowchart of the steps of a basic genetic algorithm, highlighting operators (selection, crossover, and mutation) that we will discuss in detail in the next lecture.
Whiteboard notes for this lecture can be found at:
https://www.dropbox.com/scl/fi/zdvfjtp88fl8omly7sd6u/IEE598-Lecture1E-2026-01-27-Structure_of_the_Basic_Genetic_Algorithm-Notes.pdf?rlkey=f0t4apfkyj0v9ketqxoy1xew1&dl=0
No comments:
Post a Comment