AY 2007-2008/Sem-1/Soft Computing -- Neurofuzzy techniques
From IIITM-k-wiki
Contents |
About the Course
Soft Computing is a discipline that deals with the design of hybrid intelligent systems, which is in contrast to classical hard computing technique. A consortium of computing methodologies that provides a foundation for the conception, design, and deployment of intelligent systems and aims to formalize the human ability to make rational decisions in an environment of uncertainty, imprecision, partial truth, and approximation. The main constituents of Soft computing involves neurocomputing, fuzzy logic, genetic computing and probabilistic reasoning, and their fusion in real, scientific and industrial applications.
Objective
The objective of the course is to design and develop intelligent systems in the framework of soft computing, and apply to some general and scientific application-driven environments. Students who successfully complete this course will be able to
- Have a general understanding of soft computing methodologies, including artificial neural networks, fuzzy sets, fuzzy logic, fuzzy clustering techniques and genetic algorithms;
- Study neuro-fuzzy control and inference systems;
- Have an insight into the genetic algorithms and computing, one of the powerful techniques to tackle hard optimization problems;
- Design and development of certain scientific and commercial application using computational neural network models, fuzzy models, fuzzy clustering applications and genetic algorithms in specified applications.
Instructor(s)
Principal Instructor(PI): Dr. Elizabeth Sherly; Assoc Professor, IIITM-K sherly_at_iiitmk.ac.in
Associate Instructor(AI): Dr. Raj Mathew; Asst. Professor, IIITM-K rajmathew_at_iiitmk.ac.in
Associate Instructor(AI): Ms Chitra M.T; Project Associate, IIITM-K chitra_at_iiitmk.ac.in
Class Schedule
To be Announced
Prerequisite
Basic Mathematics, Set Theory, knowledge in any programming language preferably JAVA OR C/C++ Knowledge in Mathlab/Scilab is an added advantage
Target Audience
PGDIT/MS (IT) Students, Teachers of Engineering and Science colleges, and Industry Professionals
Syllabus (in Brief)
Introduction: Introduction to soft computing; introduction to biological and artificial neural network; introduction to fuzzy sets and fuzzy logic systems
Artificial neural networks and applications: Different artificial neural network models; learning in artificial neural networks; neural network applications in control systems.
Fuzzy systems and applications: fuzzy sets; fuzzy reasoning; fuzzy inference systems; fuzzy control; fuzzy clustering; applications of fuzzy systems.
Neuro-fuzzy systems: neuro-fuzzy modeling; neuro-fuzzy control.
Genetic Algorithms: Simple GA, crossover and mutation, genetic algorithms in search and optimization
Applications: Pattern Recognitions, Image Processing, Biological Sequence Alignment and Drug Design, Robotics and Sensors, Information Retrieval Systems, Share Market Analysis, Natural Language Processing
Credit
3 Credits ( 3 lecture class + 1 practical)
Evaluation
Mid Term Exam - 30%
End Term Exam - 30%
Quiz/Assignment - 10%
Project and Lab - 30%
References
1. A. Konar, Computational Intelligence Principles, Techniques and Applications. Springer, 2005, ISBN: 3-540-20898-4
2. M. Friedman and Abraham Kandal, Introduction to Pattern Recognition- Statistical, Structural, Neural and Fuzzy Logic Approaches, World Scientific, 2005
3. Timothy J Ross, Fuzzy Logic with Engineering Applications, MCH, 1997
4. Kishan Mehrotra, Chilukuri K. Mohan and Sanjay Ranka, Elements of Artificial Neural Networks, Penram, Mumbai,1997
5. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, J.S.R. Jang, C.T. Sun, E. Mizutani, Prentice Hall, 1996
6. Mitchell, Melanie, An Introduction to Genetic Algorithms, PHI, 2004
7. Genetic Algorithms in Search, Optimization & Machine Learning by David E Goldberg-Addison Wesley
