80220152 (Evolutionary Computation and Its Applications)

Course Name: Evolutionary Computation and Its Applications

Course Number: 80220152

Program: Graduate program

Type: Elective

Credits: 2

Term Offered: Fall

Prerequisite(s): Linear Algebra, Calculus, Computer Programming, Operations Research

Instructor(s): Xinjie Yu

Textbook(s):

Xinjie Yu and Mitsuo Gen, Introduction to Evolutionary Algorithms, Springer, 2010.

Reference(s):

Eiben and Smith, Introduction to Evolutionary Computing, Springer, 2003.

Haupt and Haupt, Practical Genetic Algorithms, John Wiley, 2004.

Sivanandam and Deepa, Introduction to Genetic Algorithms, Springer, 2007.

Sumathi, Hamsapriya, and Surekha, Evolutionary Intelligence: An Introduction to Theory and Applications with Matlab, Springer, 2008.

Course Description:

     The course is about evolutionary computation, which is becoming a more attractive topic in the field of computer science, electrical engineering, operations research etc, and its applications to various optimization and learning problems.

Course Objectives and Outcomes:

     Numbers in brackets are linked to department educational outcomes

1.Students could master techniques of EAs for various optimization and learning problems. [1, 3]

2.Students could get familiar with the process of scientific research and paper writing. [5, 6, 7, 10, 11]

3.Students could learn the intuitive ideas for constrained, multimodal, multiobjective, combinatorial optimization problems and unsupervised, supervised learning problems. [1, 3, 10]

4.Students could grasp the ideas of penalizing, annealing, self-adaptive, repairing, tradeoff when designing an algorithm. [1, 3]

Course Topics:

1.Brief Introduction to Evolutionary Algorithms (EAs)

2.Improving the search ability of EAs

3.Handling Constrained Optimization by EAs

4.Handling Multimodal Optimization by EAs

5.Handling Multiobjective Optimization by EAs

6.Handling Combinatorial Optimization by EAs

7.Swarm Intelligence and Its Applications

8.Artificial Immune System and Its Applications

9.Evolutionary Programming and Its Applications

Experiment(s): Numerical experiments, which is the entitled as projects as follows.

Project(s):

Basic Optimization with EAs

 Understand and utilize evolutionary algorithms to solve basic parameter optimization problems

Constrained/Multimodal Optimization with EAs

 Understand and utilize evolutionary algorithms to solve constrained or multimodal optimization problems

Multiobjective/Combinatorial Optimization with EAs

 Understand and utilize evolutionary algorithms to solve multiobjective or combinatorial optimization problems

Learning with EAs

 Understand and utilize evolutionary algorithms to solve supervised or unsupervised learning problems

Term research project

 Utilize evolutionary algorithms to solve engineering problems in students’ research

Course Assessment:

       There are two ways of assessment in this course.

       Type A:

     Four numerical experiments/projects. 15 points for each.

     A in-class presentation to survey the cutting-edge of EAs. 30 points.

     Peer review quality for other students’ final term papers. 10 points.

       Type B:

     Two numerical experiments/projects. 15 points for each.

     A in-class presentation to survey the cutting-edge of EAs. 15 points.

     Final term performance evaluation by the instructor. 40 points.

     Final term performance evaluation by other students. 5 points.

     Peer review quality for other students’ final term papers. 10 points.