Course Description
An in-depth introduction to evolutionary computation methods and an exploration of research problems in evolutionary computation and its applications which may lead to work on a project or a dissertation.
Additional Requirements for Graduate Students:
1. Graduate students will be required to complete a substantial
research project, write a paper about it, and present their
findings to the class. The project topic should be proposed by
the student and approved by the instructor. The project should
involve novel research in the field or applying an evolutionary
computation technique to an important scientific or technological problem or a comprehensive critique and survey of a significant sub-field of evolutionary computation. The research project, paper, and presentation will constitute a significant part of the student's final grade.
2. Graduate students will also be required to present a collection of recently published research papers in the field of evolutionary computation to the class. The presentations will be graded by the instructor and will contribute to the student's final grade.
Athena Title
Evolutionary Computation Apps
Prerequisite
CSCI 2720 or CSCI 2725
Semester Course Offered
Not offered on a regular basis.
Grading System
A - F (Traditional)
Course Objectives
Evolutionary computation methods are problem solving techniques that mimic the process of natural selection. The field of evolutionary computation has attracted considerable interest in recent years. The number of publications in the field is increasing exponentially. There is a rapid growth of interest in the application of evolutionary computation methods in many fields, including computer science, engineering and bioinformatics. The main objectives of this course are: -An in-depth introduction to evolutionary computation methods. -Exploration of research problems in evolutionary computation and its applications which may lead to work on a project or a dissertation. The course is intended primarily for computer science and artificial intelligence students as well as graduate students from engineering and biological sciences departments. Graduate students from other departments may also find the course interesting.
Topical Outline
* Part I: Elements of evolutionary computation - Evolutionary computation concepts - Genetic algorithms Representation GA operators GAs in optimization GA based classifier systems - Other evolutionary computation paradigms Genetic Programming Evolution strategies Evolutionary programming Hybrid methods * Part II: Evolutionary computation applications - Computer science and electrical engineering applications: VLSI design Computer architecture and circuit design recognition - Engineering applications: Design: mechanical and aerospace, architectural ... etc. Manufacturing and scheduling, Control - Biological/bioinformatics applications * Part III: Advanced and related topics - Parallel evolutionary computation - Artificial life and/or Co-evolution - Simulated Annealing and other global optimization methods
Syllabus