18001025661 / 8527794500
info@sgtuniversity.org

Syllabus | B.Tech-Computer Science & Engineering | Soft computing

  Soft computing Learning Schedule
L T P C
Pre-requisites: C Programming 3 0 0 3

 

COURSE DESCRIPTION

This course will provide students the basic concepts of different methods and tools for processing of uncertainty in intelligent systems, such as, fuzzy models, neural networks, probabilistic models, and foundations of its using in real systems. This course covers main concepts of philosophy of artificial intelligence, hybrid intelligent systems, classification and architecture of hybrid intelligent systems.

COURSE OBJECTIVES

The objective of this course is to

  1. familiarize with soft computing concepts
  2. introduce and use the idea of Neural networks, fuzzy logic and use of heuristics based on human experience
  3. introduce and use the concepts of Genetic algorithm and its applications to soft computing using some applications.

COURSE OUTCOMES

On completion of this course, the students will be able to

  1. identify and describe soft computing techniques and their roles in building intelligent machines
  2. recognize the feasibility of applying a soft computing methodology for a particular problem
  3. apply fuzzy logic and reasoning to handle uncertainty and solve engineering problems, genetic algorithms to combinatorial optimization problems and neural networks to pattern classification and regression problems
  4. effectively use modern software tools to solve real problems using a soft computing approach and evaluate various soft computing approaches for a given problem.

COURSE CONTENT

Unit I: Artificial Neural Networks

Basic-concepts-single layer perception-Multi layer perception-Supervised and unsupervised learning back propagation networks, Application.

Unit II: Fuzzy Systems

Fuzzy sets and Fuzzy reasoning-Fuzzy matrices-Fuzzy functions-decomposition-Fuzzy automata and languages- Fuzzy control methods-Fuzzy decision making, Applications.

Unit III: Neuro-Fuzzy Modeling

Adaptive networks based Fuzzy interfaces-Classification and Representation trees-Data dustemp algorithm –Rule base structure identification-Neuro-Fuzzy controls

Unit IV:  Genetic Algorithm

Survival of the fittest-pictures computations-cross over mutation-reproduction-rank method-rank space method, Application.

Unit V: Artificial Intelligence

AI Search algorithm-Predicate calculus rules of interface – Semantic networks-frames-objects-Hybrid models, applications.

TEXT BOOKS

  1. E – Neuro Fuzzy and Soft computing – Jang J.S.R., Sun C.T and Mizutami, Prentice hall New Jersey, 1998
  2. Fuzzy Logic Engineering Applications – Timothy J.Ross, McGraw Hill, NewYork, 1997.
  3. Fundamentals of Neural Networks – Laurene Fauseett, Prentice Hall India, New Delhi, 1994.

REFERENCE BOOKS

  1. Introduction to Artificial Intelligence – E Charniak and D McDermott, Pearson Education
  2. Artificial Intelligence and Expert Systems – Dan W. Patterson, Prentice Hall of India.
ADMISSIONS 2021