Scribd
Upload
116 views

Soft Computing

This document outlines a course on soft computing techniques. The course introduces concepts in artificial neural networks, supervised learning, unsupervised learning, fuzzy logic, and genetic algorithms. Upon completing the course, students will be able to demonstrate knowledge of these techniques, analyze and design soft computing solutions, and apply techniques to solve complex problems and issues in business intelligence and forecasting. The course is divided into 5 units covering these topics over 45 periods.

Uploaded by

Neelima Malchi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
116 views

Soft Computing

This document outlines a course on soft computing techniques. The course introduces concepts in artificial neural networks, supervised learning, unsupervised learning, fuzzy logic, and genetic algorithms. Upon completing the course, students will be able to demonstrate knowledge of these techniques, analyze and design soft computing solutions, and apply techniques to solve complex problems and issues in business intelligence and forecasting. The course is divided into 5 units covering these topics over 45 periods.

Uploaded by

Neelima Malchi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

SOFT COMPUTING

PRE-REQUISITES:
A course on “Multi variable calculus and differential equations”
COURSE DESCRIPTION:
Concepts on Soft Computing Techniques; Artificial Neural Networks; Supervised Learning;
Unsupervised Learning; Fuzzy logic; Genetic Algorithms.
COURSE OUTCOMES:
On successful completion of the course, students will be able to:
CO1. Demonstrate knowledge in
 Artificial Neural Networks
 Supervised Learning Networks
 Unsupervised Learning Networks
 Fuzzy sets, relations and measures
 Genetic Operators
CO2. Analyze neural network architectures, Fuzzy systems and Genetic algorithms.
CO3. Design soft computing solutions for real life computational problems.
CO4. Use soft computing techniques to solve complex computational problems.
CO5. Create algorithms using soft computing techniques.
CO6. Apply contextual knowledge to solve problems related to societal issues like Business
Intelligence, Forecasting.
CO-PO Mapping:

PO1 PO2 PO3 PO4 PO5 PO6

CO1 √

CO2 √

CO3 √

CO4 √

CO5 √

CO6 √
DETAILED SYLLABUS:

UNIT-I: INTRODUCTION TO SOFT COMPUTING AND ARTIFICIAL NEURAL


NETWORKS (9 Periods)
Soft Computing: Neural networks, Application scope of neural networks, Hybrid systems, Soft
computing, Applications of soft computing.
Artificial Neural Networks: Fundamentals, Evolution, Basic Models, Terminologies, Hebb
network.
UNIT-II: SUPERVISED LEARNING NETWORKS (9 Periods)
Perceptron Networks: Theory, Perceptron learning rule, Architecture, Flowchart for training
process, Perceptron training algorithm for single and multiple output classes, Perceptron network
testing algorithm.
Back-Propagation Networks: Theory, Architecture, Flow chart for training process, Training
algorithm, Learning factors of backpropagation networks, Testing algorithm for back-
propagation networks.
UNIT-III: UNSUPERVISED LEARNING NETWORKS (9 Periods)
Unsupervised Learning Networks: Fixed weight competitive nets, Kohonen self-organizing
feature maps, learning vector quantization, Counter-propagation networks, Adaptive response
theory network.
UNIT-IV: FUZZY LOGIC (9 Periods)
Classical Sets and Fuzzy Sets: Classical sets- Operations, Properties, Function mapping; Fuzzy
sets- Operations, Properties.
Classical Relations and Fuzzy Relations: Cartesian product of relation, Classical relations, Fuzzy
relations, Tolerance and equivalence relations, Non-interactive fuzzy sets.
UNIT-V: FUZZY SYSTEMS AND GENETIC ALGORITHMS (9 Periods)
Fuzzy Arithmetic and Fuzzy Measures: Fuzzy arithmetic, Extension principle, Fuzzy measures,
Measures of fuzziness. Genetic Algorithms: Genetic operators, Working principle, Fitness
function, reproduction.
Total Periods: 45
TEXT BOOK:
1. S. N. Sivanandan and S. N. Deepa, Principles of Soft Computing, Wiley India, Second
Edition, 2011.
REFERENCE BOOKS:
1. Jyh-Shing Roger Jang, Chuen-Tsai Sun and Eiji Mizutani, Neuro-Fuzzy and Soft Computing,
Prentice-Hall India, 2003.
2. S. Rajasekaran and G. A. Vijayalakshmi Pai, Neural Networks, Fuzzy Logic and Genetic
Algorithms: Synthesis and Applications, PHI Learning Private Ltd, 2011.

You might also like