Resource: Introduction to Evolutionary Computing, A.E.Eliben


Outline

  1. recombination
  2. parent selection
  3. survivor selection
  4. self-adaptation

1. Recombination

1.1 Basic recombination

two parents --> one child

There are two recombination variants distinguished by the manner of recombining parent allels:

  • discrete recombination: one of the parent alleles is randomly chosen with equal chance for either parents.
  • intermediate recombination: the values of parent alleles are averaged.

Formally, given two parent vectors x and y, one child z is created, where

for all i ∈ {1,...,n}.

1.2 An extension

An extension of this scheme allows the use of more than two recombinants, because the two parents x and y are drawn randomly for each position i ∈ {1,...,n} in the offspring anew.

These drawings take the whole population of μ individuals into consideration, and the result is a recombination operator with possibly more than two individuals contributing to the offspring.

The exact number of parents, however, cannot be defined in advance. This multiparent variant is called global recombination. To make terminology unambiguous, the original variant is called local recombination.

2. Parent Selection

3. Survivor Selection

4. Self-adaptation

5. Example application

Evolutionary Computing: 5. Evolutionary Strategies(2)的更多相关文章

  1. Evolutionary Computing: 5. Evolutionary Strategies(1)

    resource: Evolutionary computing, A.E.Eiben Outline What is Evolution Strategies Introductory Exampl ...

  2. Evolutionary Computing: 4. Review

    Resource:<Introduction to Evolutionary Computing> 1. What is an evolutionary algorithm? There ...

  3. Evolutionary Computing: 1. Introduction

    Outline 什么是进化算法 能够解决什么样的问题 进化算法的重要组成部分 八皇后问题(实例) 1. 什么是进化算法 遗传算法(GA)是模拟生物进化过程的计算模型,是自然遗传学与计算机科学相互结合的 ...

  4. Evolutionary Computing: [reading notes]On the Life-Long Learning Capabilities of a NELLI*: A Hyper-Heuristic Optimisation System

    resource: On the Life-Long Learning Capabilities of a NELLI*: A Hyper-Heuristic Optimisation System ...

  5. Evolutionary Computing: Assignments

    Assignment 1: TSP Travel Salesman Problem Assignment 2: TTP Travel Thief Problem The goal is to find ...

  6. Evolutionary Computing: multi-objective optimisation

    1. What is multi-objective optimisation [wikipedia]: Multi-objective optimization (also known as mul ...

  7. Evolutionary Computing: 3. Genetic Algorithm(2)

    承接上一章,接着写Genetic Algorithm. 本章主要写排列表达(permutation representations) 开始先引一个具体的例子来进行表述 Outline 问题描述 排列表 ...

  8. Evolutionary Computing: 2. Genetic Algorithm(1)

    本篇博文讲述基因算法(Genetic Algorithm),基因算法是最著名的进化算法. 内容依然来自博主的听课记录和教授的PPT. Outline 简单基因算法 个体表达 变异 重组 选择重组还是变 ...

  9. 不就ideas嘛,谁没有!

    20160214 survey of current RDF triple storage systems survey of semantic web stack inference mechani ...

随机推荐

  1. 浅谈php中使用websocket

    在PHP中,开发者需要考虑的东西比较多,从socket的连接.建立.绑定.监听等都需要开发者自己去操作完成,对于初学者来说,难度方面也挺大的,所以本文的思路如下: 1.socket协议的简介 2.介绍 ...

  2. 1.多线程-NSThread

    1.在主线程执行多次NSLog模拟耗时操作 结果,卡住主线程 解决方案: performSelectorInBackground让程序在后台执行   2.pthread的使用 开辟子线程,执行一个函数 ...

  3. 关于UIView的显示问题

    今天在倒腾PP助手SDK的接入,游戏框架使用的是cocos2d-x,因为不熟悉iOS的UIKit,所以费了点功夫终于让SDK的登录页面显示出来了,问题来了,在iOS设备landscape显示模式UI显 ...

  4. iOS · UILabel加删除线

    创建自定义子类DeleteLineLabel,继承自UILabel,然后在自定义子类DeleteLineLabel中 方法一(上下文): - (void)drawRect:(CGRect)rect { ...

  5. 【原】十分钟搞定pandas

    http://www.cnblogs.com/chaosimple/p/4153083.html 本文是对pandas官方网站上<10 Minutes to pandas>的一个简单的翻译 ...

  6. eclipse 自动排版

    自动排版:  ctrl + i 同名变量高亮: shift+alt+ o 导包:  shift+ctrl +o

  7. ubuntu安装

    今天在win10下安装Ubuntu,结果没经验导致win10找不回来了,我再好好整理些思路 安装前要做一个ghost,万一出现问题可以用来恢复系统! 1,我使用USB Installer 在http: ...

  8. Linux网络配置基础

    linux网络配置常见有两种:桥接模式(Bridge)与NAT模式,还有一种Host-Only模式由于其局限性通常被舍弃就不加以说明了,下面我们介绍下桥接模式(Bridge)和NAT模式. 桥接模式( ...

  9. xml 方式更新和获取 配置文件 appSettings 节点 解决办法

    最近在搞一个小程序,会用到动态修改配置文件来进行处理,在百度上找了很多办法,但是始终达不到我预想的效果,先列出程序运行环境和开发工具版本: 开发工具:VS2010 .Net 运行环境:4.0 有两种方 ...

  10. VBA中方法传参

    将变量做为参数传递给方法 Sub Test() Dim a As Integer a = Add a Debug.Print a '引用传递,a的值发生了变化,输出101 End Sub Functi ...