CpEng 358 /EE 367/System Eng 367

COMPUTATIONAL INTELLIGENCE (CI)

 

All students, graduate and undergraduate are encouraged to take this course.
We will explore and exploit the field of Computational Intelligence.

The future is in intelligence! Don't miss out.

PRESCRIBED TEXTBOOK :

 

Computational Intelligence - An Introduction by Andries P Engelbrecht, Second Edition

 

COURSE CONTENT

 

This is the first course of a series of four courses (358/367- Computational Intelligence, 458- Adaptive Critics (Spring 08), 401- Advanced Neural Networks and Hardware (FS08) and 301-Adaptive Devices, Circuits and Systems (SP09)) to be offered and will cover the five main paradigms of Computational Intelligence (CI) and their integration to develop hybrid systems. This course is an introductory level course and will lead students to courses focused in depth in a particular paradigm (ANNs, EC, SI, AIS, FS).

 

Introduction to CI:

The following CI paradigms are covered: artificial neural networks, evolutionary computing, swarm intelligence, artificial immune systems and fuzzy systems. While individual techniques from these CI paradigms have been applied successfully to solve real-world problems, the current trend is to develop hybrids of paradigms, since no one paradigm is superior to the others in all situations. In doing so, we are able capitalize on the respective strengths of the components of the hybrid CI system and eliminate weakness of individual components.

 

Part I - Artificial Neural Networks (ANNs):

The Artificial Neuron; Supervised Learning Neural Networks; Unsupervised Learning Neural Networks; Radial Basis Function Networks. This part will be introductory in nature since most of the course involves EC, SI, and FS methods for training and developing ANN structures.

 

Part II - Evolutionary Computing (ECs):

A brief introduction of the following EC techniques - Genetic Algorithms (GAs), Genetic Programming (GP), Evolutionary Programming (EP), Evolutionary Strategies (ESs). Applications of these algorithms (GAs, ESs) to train neural networks will be emphasized.

 

Part III - Swarm Intelligence (SI):

Particle Swarm Optimization (PSO); Ant Colony Optimization;  Cultural Evolution. Applications of PSO to train neural networks will be emphasized. The integration of Swarm and Cultural evolution will be discussed.

 

Part IV - Artificial Immune Systems (AIS):

The biological immune system is a highly parallel and distributed adaptive system. It uses learning, memory, and associative retrieval to solve recognition and classification tasks. Artificial Immune Systems is a new computational approach for the CI community. It is an excellent tool for solving engineering problems. The design of robust controllers using AIS will be covered among other applications.

Part V - Fuzzy Systems (FS):

Fuzzy Systems; Fuzzy Logic; Fuzzy Interference Systems; Fuzzy Controllers; Rough Sets.

 

Part VI: Hybrid Systems:

The integration of these CI paradigms in the development of hybrid systems for solving engineering problems will be taught. Applications will include design of optimal digital circuits, mapping and routing on hardware such as FPGA, modeling nonlinear systems, design of optimal, adaptive and nonlinear controllers for systems, modeling and control of power systems, optimal placements of FACTS and other power system devices, image and signal processing, biometrics applications, robotics, etc.

 

Students are required to have some programming background in MATLAB or C/C++.

 

Prerequisites: Statistics 217 (or Instructor's permission)

 

Please email any questions to Dr. G K Venayagamoorthy at ganeshv@mst.edu