Page 86 - R2017-REC-ECE-UG Syllabus

Department of ECE, REC

2. Willliam K Pratt, “Digital Image Processing”, John Willey, 2002.
3. Malay K. Pakhira, “Digital Image Processing and Pattern Recognition”, First Edition, PHI
Learning Pvt. Ltd., 2011.
4. http://eeweb.poly.edu/~onur/lectures/lectures.html.
5. http://www.caen.uiowa.edu/~dip/LECTURE/lecture.html

EC17E66 SOFT COMPUTING L T P C
3 0 0 3
OBJECTIVES:
The students are able to:
• To introduce fuzzy set theory and fuzzy inference systems.
• To teach different optimization techniques
• To introduce neural networks using supervised and unsupervised learning
• To learn neuro-fuzzy modeling
• To teach various applications of computational intelligence

UNIT I FUZZY SET THEORY 10
Introduction to Neuro - Fuzzy and Soft Computing - Fuzzy Sets - Basic Definition and Terminology
- Set-theoretic Operations - Member Function Formulation and Parameterization -
Fuzzy Rules and Fuzzy Reasoning - Extension Principle and Fuzzy Relations - Fuzzy If-Then Rules - Fuzzy
Reasoning - Fuzzy Inference Systems - Mamdani Fuzzy Models - Sugeno Fuzzy Models - Tsukamoto Fuzzy
Models - Input Space Partitioning and Fuzzy Modeling.

UNIT II OPTIMIZATION 8
Derivative-based Optimization - Descent Methods - The Method of Steepest Descent - Classical Newton‘s
Method - Step Size Determination - Derivative-free Optimization - Genetic Algorithms - Simulated Annealing
- Random Search - Downhill Simplex Search.

UNIT III NEURAL NETWORKS 10
Supervised Learning Neural Networks - Perceptrons - Adaline - BackpropagationMutilayer
Perceptrons - Radial Basis Function Networks - Unsupervised Learning Neural Networks -
Competitive Learning Networks - Kohonen Self-Organizing Networks - Learning Vector Quantization -
Hebbian Learning.

UNIT IV NEURO FUZZY MODELING 9
Adaptive Neuro-Fuzzy Inference Systems - Architecture - Hybrid Learning Algorithm - Learning Methods
that Cross-fertilize ANFIS and RBFN - Coactive Neuro Fuzzy Modeling- Framework Neuron Functions for
Adaptive Networks - Neuro Fuzzy Spectrum.

UNIT V APPLICATIONS OF COMPUTATIONAL INTELLIGENCE 8
Printed Character Recognition - Inverse Kinematics Problems - Automobile Fuel Efficiency Prediction -
Soft Computing for Color Recipe Prediction.

TOTAL= 45 PERIODS

OUTCOMES:
Upon completion of the course, students will be able to:
• Ability to appreciate the significance and role of fuzzy logic
• Apply various optimization algorithms.
• Ability to comprehend the role of neural network and design various neural networks

Curriculum and Syllabus | B.E. Electronics and Communication Engineering | R2017 Page 86