Lecture_3 - iologically Inspired Methods(7CEMM708...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

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

Unformatted text preview: iologically Inspired Methods (7CEMM708) iologically Inspired Methods (7CEMM708) The Continuous Genetic Algorithm The Continuous Genetic Algorithm Dr. Lei Ren Division of Engineering, King’s College London, Strand, London, WC2R 2LS E-mail: [email protected] Room 244, Strand Building, Strand Campus Introduction Introduction The Continuous Genetic Algorithm Binary GA is limited by quantisation level for continuous problem A Bessel function v.s. A 6-bit binary quantized version of the same function Precision No. of Bits Size of Chromosome Speed of GA ontinuous Genetic Algorithm ontinuous Genetic Algorithm Introduction Introduction The Continuous Genetic Algorithm Require less storage than the binary GA A single floating-point number v.s. N bits ‘0’ and ‘1’ Allows representation to the machine precision Inherently faster than the binary GA as no encoding & decoding needed Deal with complex problem with high dimensionality M ore logical to represent variables by floating-point numbers when the problems are continuous ontinuous Genetic Algorithm ontinuous Genetic Algorithm Introduction Introduction The Continuous Genetic Algorithm Initial population Rating Selection Reproduction Mutation ontinuous Genetic Algorithm ontinuous Genetic Algorithm Components of Continuous GA Components of Continuous GA ontinuous Genetic Algorithm ontinuous Genetic Algorithm Variables and Cost Function The optimisation variables are represented by chromosome chromosome = [ p 1 , p 2 , p 3 , . . . , p N ] The cost is evaluated by cost function cost = f ( chromosome ) = f ( p 1 , p 2 , p 3 , . . . , p N ) Variable values are represented as floating-point numbers, no longer need to consider how many bits are necessary to accurately represent a value No encoding & decoding before cost function evaluation Only limited to the internal precision and roundoff error of computers Natural form of real-valued cost function can be used directly Variables and Cost Function Find the minimum of: f(x,y)= x·sin(4x)+1.1·y·sin(2y) Subject to: ≤ x ≤ 10 and 0 ≤ y ≤ 10 chromosome = [ x, y ] N var = 2 ontinuous Genetic Algorithm ontinuous Genetic Algorithm Components of Continuous GA Components of Continuous GA The GA starts with an initial population with N pop chromosomes With a N pop × N var matrix filled with randomly generated real values Initial Population Initial population of 8 Uniform Randomly Generated Chromosomes Population matrix 8×2 ontinuous Genetic Algorithm ontinuous Genetic Algorithm Components of Continuous GA Components of Continuous GA N pop chromosomes are ranked from lowest cost to highest cost...
View Full Document

This note was uploaded on 03/27/2010 for the course MSC ADVANCE SO taught by Professor Dr.markhurman during the Spring '09 term at King's College London.

Page1 / 36

Lecture_3 - iologically Inspired Methods(7CEMM708...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online