《智能优化算法及编程》课程教学大纲

一、课程名称

1、中文名称:智能优化算法及编程

2、英文名称:Intelligent Optimization Algorithm and Programming

二、课程概况

课程类别:专业学位课       学时数: 32        学分数:2

适用专业:交通运输规划与管理/交通运输工程        开课学期:第一学期

开课单位:文理学院

三、大纲编写人:蒋开明

四、教学目的及要求

通过本课程的学习,要求学生系统地掌握智能算法的基本内容、基本原理和应用范畴。较系统地学习神经网络算法、支撑向量机、遗传算法和粒子群算法的主要内容。通过实验对MatLab在计算智能中的应用能有较深入的了解,对所学内容中的主要算法能进行数值模拟。

五、课程主要内容及先修课程

第一章 预备知识                                          8学时

1. 1 多元函数与超曲面

1. 2 求函数最值

1. 3 向量范数

1. 4 随机数的生成

第二章 人工神经网络                                    8学时

2.1 多层前向网

2.2 径向基函数

2.3 回归神经网络

第三章 支撑向量机                                       4学时

3.1 最优分离超平面

3.2 支撑向量机

3.3 SVM学习算法

第四章 遗传算法                                          6学时

4.1 简单遗传算法

4.2 个体与种群

4.3 遗传算子

4.4 模式

第五章 粒子群算法                                       6学时

5.1 基本粒子群算法

5.2 带惯性权重和收缩因子的粒子群算法

5.3 改进粒子群算法

5.4 应用算例

先修课程:离散数学、高等数学、程序设计

六、课程教学方法

本课程主要采用课堂讲授的方式, 辅以利用Matlab实现本课程中算法的数值模拟。

七、课程考核方式

闭卷考试(80%)+平时(20%)

八、课程使用教材

褚蕾蕾等编著,《计算智能的数学基础》,科学出版社,2002.9

九、课程主要参考资料

1、杨淑莹,张桦. 群体智能与仿生计算----Matlab技术实现,电子工业出版社, 2012

2、刘衍民,牛奔. 新型粒子群算法理论与实践,科学出版社,2012

3、玄光男,程润伟著;于歆杰,周根贵译.遗传算法与工程优化,清华大学出版社,2003(2009重印)

 

 

 

Course Programme for Intelligent Optimization Algorithm and Programming

1. Name of the Course

Chinese Name:智能优化算法及编程

English Name: Intelligent Optimization Algorithm and Programming

2. Overview of the Course

Class hours: 32              Credit: 2

Profession: Transportation Planning and Management, Transportation Engineering

3. The WriterKaiming Jiang

4. The Objective and Requirement of the Course

Through studying this course, students are required to systematically grasp the basic content, basic principles and application fields of several intelligent algorithms including neural network algorithm, support vector machine, genetic algorithm and particle swarm optimization algorithm. The application of MatLab in computational intelligence can be better understood through experiments, and the several intelligent algorithms can be numerically simulated.

5. Main Content of the Course and Pre-course

Chapter 1 Basics                                                                         8 hours.

1.1 Multivariate functions and hypersurfaces

1.2 Maximum and minimum of functions.

1.3 Vector norm

1.4 Generation of random numbers

Chapter 2 Artificial neural network                                            8 hours.

2.1 Multilayer forward neural network

2.2 Radial basis functions

2.3 Recurrent neural network

Chapter 3 Support vector machine                                             4 hours.

3.1 Optimal separation hyperplane

3.2 Support vector machine

3.3 SVM learning algorithm

Chapter 4 Genetic algorithm                                                      6 hours.

4.1 Simple genetic algorithm

4.2 Individuals and populations

4.3 Genetic operators

4.4 Mode

Chapter 5 Particle swarm optimization algorithm                     6 hours.

5.1 Basic particle swarm optimization algorithm

5.2 Particle swarm optimization algorithm with inertia weight and contraction factor

5.3 Improved particle swarm optimization algorithm

5.4 Application examples

Pre-courses: Discrete mathematics, Advanced mathematics, and Programming.

6. Teaching Methods

This course mainly uses the classroom teaching method, supplemented by the use of MATLAB to achieve the numerical simulation of the algorithm in this course.

7. Methods of Examination

Closed-book exam (80%) + Daily performance (20%)

8. Textbook

1. Zhu Leilei et al., Mathematical foundation of computational intelligence, Science Press, 2002. 9

9. Main References

1. Yang Shuying, Zhang Hua. Swarm intelligence and bionic computation ----Matlab technology, Electronic industry press, Two thousand and twelve

2. Liu Yanmin, Niu Ben. New particle swarm algorithm, Science Press, 2012

3. Xuan Guangnan, Cheng Runwei. Genetic algorithm and engineering Optimization, Tsinghua University Press, 2003 (2009 Reprint)