The modified genetic algorithm that is analyzed with the schema theorem is feasible 以模式定理論述改進(jìn)遺傳算法的可行性。
About genetic algorithms, its basic principle, operation, schema theorem, and the realization in the computer are discussed firstly 對(duì)于遺傳算法(ga),本文討論了它的基本原理、操作步驟、模式理論及ga的計(jì)算機(jī)實(shí)現(xiàn)問(wèn)題,以及簡(jiǎn)單遺傳算法的幾種改進(jìn)措施。
(4 ) we introduce basic theory of schemas in learning and evolution, that is, genetic algorithm . we discuss the definition of schemas, several relative concepts and schema theorem in genetic algorithm (4)介紹圖式學(xué)習(xí)和進(jìn)化的基礎(chǔ)理論??遺傳算法,給出了遺傳算法中圖式的定義、相關(guān)的幾個(gè)概念以及圖式定理。
The major tasks include : ( 1 ) expand the schema theorem for ga . the schema theorem with binary coding advanced by professor holland is expanded to limited integer, letter, floating point numbers the number of which value is limited, and their hybrid coding . ( 2 ) put forward replacing by the excellent chromosome ga ( recga ), superiority colony first ga ( scfga ) and improve the ga; ( 3 ) make probability convergence analysis of recga using the theory of markov chain, random process; ( 4 ) make convergence analysis of scfga using the principle of contractive mapping in functional analysis theory; ( 5 ) design the test programs ( cap ) to resolve np problems ( course arrangement ) with gas; based on recga, modify the arithmetic and then conduct tests 主要有以下幾方面工作:(1)將二進(jìn)制編碼遺傳算法的模式定理擴(kuò)展到由有限整數(shù)、字母或取值個(gè)數(shù)有限的浮點(diǎn)數(shù)編碼,或它們混合編碼的遺傳算法范圍;(2)提出最佳個(gè)體替換策略遺傳算法(recga)、優(yōu)勢(shì)群體優(yōu)先策略遺傳算法(scfga),對(duì)遺傳算法進(jìn)行改進(jìn);(3)使用隨機(jī)過(guò)程理論markov鏈對(duì)recga進(jìn)行了收斂性分析;(4)使用泛函分析理論壓縮映射原理對(duì)scfga進(jìn)行了收斂性分析;(5)使用遺傳算法設(shè)計(jì)了解決np類問(wèn)題(排課問(wèn)題)的測(cè)試程序(cap),并根據(jù)recga對(duì)算法進(jìn)行改進(jìn)并進(jìn)行測(cè)試。
The major tasks include : ( 1 ) expand the schema theorem for ga . the schema theorem with binary coding advanced by professor holland is expanded to limited integer, letter, floating point numbers the number of which value is limited, and their hybrid coding . ( 2 ) put forward replacing by the excellent chromosome ga ( recga ), superiority colony first ga ( scfga ) and improve the ga; ( 3 ) make probability convergence analysis of recga using the theory of markov chain, random process; ( 4 ) make convergence analysis of scfga using the principle of contractive mapping in functional analysis theory; ( 5 ) design the test programs ( cap ) to resolve np problems ( course arrangement ) with gas; based on recga, modify the arithmetic and then conduct tests 主要有以下幾方面工作:(1)將二進(jìn)制編碼遺傳算法的模式定理擴(kuò)展到由有限整數(shù)、字母或取值個(gè)數(shù)有限的浮點(diǎn)數(shù)編碼,或它們混合編碼的遺傳算法范圍;(2)提出最佳個(gè)體替換策略遺傳算法(recga)、優(yōu)勢(shì)群體優(yōu)先策略遺傳算法(scfga),對(duì)遺傳算法進(jìn)行改進(jìn);(3)使用隨機(jī)過(guò)程理論markov鏈對(duì)recga進(jìn)行了收斂性分析;(4)使用泛函分析理論壓縮映射原理對(duì)scfga進(jìn)行了收斂性分析;(5)使用遺傳算法設(shè)計(jì)了解決np類問(wèn)題(排課問(wèn)題)的測(cè)試程序(cap),并根據(jù)recga對(duì)算法進(jìn)行改進(jìn)并進(jìn)行測(cè)試。