SOFT COMPUTING TECHNIQUES

Paper Code: 
MCA 325C
Credits: 
04
Periods/week: 
04
Max. Marks: 
100.00
Objective: 

Course Objectives:

This course enables the students to

  1. Understand the basic principles, techniques, and applications of soft computing.
  2. Understand basic concepts of Soft Computing including Artificial Neural Networks, Fuzzy Logic and Genetic Algorithms.
  3. Gain the mathematical background for carrying out the optimization associated with neural network learning.
  4. Develop acquaintance with current research problems and research methods in Soft Computing
  5. Apply the concept of hybrid system
  6. Extend the basic skills necessary to pursue research in Soft Computing

 

 

Course Outcomes(COs):

 

Learning Outcome (at course level)

 

Learning and teaching strategies

Assessment Strategies

  1. Understand different types of soft computing techniques and its applications
  2. Thorough exploration of concept related to Fuzzy Logic and its different popular models
  3. Gain deeper knowledge of Artificial Neural Networks.
  4. Study genetic algorithms and its applicability in research oriented problems
  5. Pertain the concept and applicability of hybrid systems
  6. Apply current research problems and research methods in soft computing

Approach in teaching:

Interactive Lectures,

Modeling, Discussions, implementing enquiry based learning, student centered approach, Through audio-visual aids

 

Learning activities for the students:

Experiential Learning, Presentations, Discussions, Quizzes and Assignments

 

  • Assignments
  • Written test in classroom
  • Classroom Activity
  • Continuous Assessment
  • SemesterEnd Examination
 

 

12.00
Unit I: 

Introduction to Soft Computing

Introduction of Hard and Soft Computing, Unique features of Soft computing, Components of Soft computing, Fuzzy Computing, Evolutionary Computation, Genetic Algorithm, Swarm Intelligence, Ant Colony Optimizations, Neural Network, Machine Learning , Associative Memory, Adaptive Resonance Theory, Introduction to Deep Learning

14.00
Unit II: 

Fuzzy Logic

Basic concepts of fuzzy logic, Fuzzy sets and Crisp sets, Fuzzy set theory and operations, Properties of fuzzy sets, Fuzzy and Crisp relations, Fuzzy to Crisp conversion, Membership functions, interference in fuzzy logic, fuzzy if-then rules, Fuzzy implications and Fuzzy algorithms, Fuzzyfications & Defuzzificataions, Fuzzy Inference Systems, Mamdani Fuzzy Model, Sugeno Fuzzy Model, Fuzzy Controller, applications.

14.00
Unit III: 

Neural Networks

Introduction and Architecture: Neuron, Nerve structure and synapse, Artificial Neuron and its model, Neural network architecture: single layer and multilayer feed forward networks, recurrent networks. Back propagation networks architecture: perceptron model, solution, single layer artificial neural network, multilayer perception model; back propagation learning methods, back propagation algorithm, applications.

10.00
Unit IV: 

Genetic Algorithms

Basic concepts of GA, working principle, procedures of GA, flow chart of GA, Genetic representations, (encoding) Initialization and selection, Genetic operators, Mutation, Generational Cycle, applications.

10.00
Unit V: 

Hybrid Systems

Integration of neural networks, fuzzy logic and genetic algorithms. GA Based Back Propagation Networks, Fuzzy Back Propagation Networks, Fuzzy Associative Memories, Simplified Fuzzy ARTMAP

 

ESSENTIAL READINGS: 

Essential Readings:

·         S. Rajasekaran and G.A. Vijaylakshmi Pai, “Neural Networks Fuzzy Logic, and Genetic Algorithms”, Prentice Hall of India 2007.

·         K.H. Lee. First Course on Fuzzy Theory and Applications, Springer-Verlag, 2005

·         D. K. Pratihar, Soft Computing, Narosa, 2008

  • D. E. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley
REFERENCES: 

E- Resources

Journals

 

Academic Year: 
2023-24
  • Printer-friendly version