‌

‌
Faculty‌ ‌ Faculty‌‌of‌‌Engineering‌‌&‌‌Technology‌ ‌
‌
Programme‌‌ [Link]‌‌-computer‌‌Science‌‌&‌‌engineering‌‌with‌‌specialization‌‌in‌‌Artificial‌‌
Name‌ ‌ Intelligence‌‌&‌‌Machine‌‌Learning‌ ‌
Course‌‌Name‌‌
Soft‌‌Computing‌‌-‌‌CSA021‌ ‌
&‌‌Code‌ ‌
Version,‌‌Date‌‌ ‌ ‌
of‌‌Approval‌ ‌
Contact‌‌Hours‌ ‌ 3‌ ‌ Credits:‌‌4‌ ‌
Pre-requisites‌ ‌
/‌‌co-requisites‌ ‌
Type‌‌of‌‌course‌‌ Core‌ ‌
(foundation/p‌ ‌
rogramme‌‌
core‌‌elective‌ ‌
Teaching‌‌ ‌
Faculty‌ ‌
‌ This‌‌course‌‌will‌‌cover‌‌fundamental‌‌concepts‌‌used‌‌in‌‌Soft‌‌computing.‌‌The‌‌concepts‌‌of‌‌Fuzzy‌‌
COURSE‌‌ logic‌ ‌(FL)‌ ‌will‌ ‌be‌ ‌covered‌ ‌first,‌ ‌followed‌ ‌by‌ ‌Artificial‌ ‌Neural‌ ‌Networks‌ ‌(ANNs)‌ ‌and‌‌
DESCRIPTIO‌ optimization‌ ‌techniques‌ ‌using‌ ‌Genetic‌ ‌Algorithm‌ ‌(GA).‌ ‌Applications‌ ‌of‌ ‌Soft‌ ‌Computing‌‌
N‌ ‌ techniques‌‌to‌‌solve‌‌a‌‌number‌‌of‌‌real‌‌life‌‌problems‌‌will‌‌be‌‌covered‌‌to‌‌have‌‌hands‌‌on‌‌practices.‌ ‌

COURSE‌‌ The‌ ‌primary‌ ‌objective‌ ‌of‌ ‌this‌ ‌course‌ ‌is‌ ‌to‌ ‌provide‌ ‌an‌ ‌introduction‌ ‌to‌ ‌the‌ ‌basic‌ ‌principles,‌‌
OBJECTIVES‌ ‌ techniques,‌ ‌and‌ ‌applications‌ ‌of‌ ‌soft‌ ‌computing.‌ ‌Upon‌ ‌successful‌‌completion‌‌of‌‌the‌‌course,‌‌
students‌‌will‌‌have‌‌an‌‌understanding‌‌of‌‌the‌‌basic‌‌areas‌‌of‌‌Soft‌‌Computing‌‌including‌‌Artificial‌‌
Neural‌ ‌Networks,‌ ‌Fuzzy‌ ‌Logic‌ ‌and‌ ‌Genetic‌ ‌Algorithms.‌ ‌Provide‌ ‌the‌ ‌mathematical‌‌
background‌‌for‌‌carrying‌‌out‌‌the‌‌optimization‌‌associated‌‌with‌‌neural‌‌network‌‌learning.‌‌Aim‌‌of‌‌
this‌ ‌course‌ ‌is‌ ‌to‌ ‌develop‌ ‌some‌ ‌familiarity‌ ‌with‌ ‌current‌ ‌research‌ ‌problems‌ ‌and‌ ‌research‌‌
methods‌‌in‌‌Soft‌‌Computing‌‌by‌‌working‌‌on‌‌a‌‌research‌‌or‌‌design‌‌project.‌ ‌
COURSE‌‌
The‌‌Completion‌‌of‌‌this‌‌Course‌‌will‌‌Enable‌‌the‌‌Students‌‌to‌‌be‌‌able‌‌to‌‌Learn‌ ‌
OUTCOMES‌ ‌
CO1:‌D‌ efine‌‌the‌‌basic‌‌concepts‌‌of‌‌soft‌‌computing.‌ ‌
CO2:‌E‌ xplain‌‌applications‌‌&‌‌operations‌‌of‌‌Fuzzy‌‌Logic‌‌in‌‌real‌‌life‌‌problems.‌ ‌
CO3:‌A‌ pply‌‌different‌‌FIS‌‌models‌‌to‌‌solve‌‌optimization‌‌problems.‌ ‌
CO4:‌ ‌Analyse‌ ‌and‌ ‌examine‌ ‌Evolutionary‌ ‌and‌ ‌swarm‌ ‌algorithms‌ ‌in‌ ‌solving‌ ‌real‌ ‌world‌‌
Multi-Objective‌‌optimization‌‌problems‌ ‌
CO5:‌‌‌Discuss‌‌applications‌‌of‌‌Soft‌‌Computing‌‌and‌‌solve‌‌Problems‌‌in‌‌Varieties‌‌of‌‌Application‌‌
Domains.‌ ‌
Course‌‌Outline‌ ‌
Week‌‌ ‌ Module‌ ‌ CO‌‌Mapping‌ ‌

1‌ ‌ Concept‌‌of‌‌computing‌‌systems.‌‌What‌‌is‌‌Soft‌ CO1‌‌ ‌
Computing?‌ ‌
2‌ ‌ "Soft"‌‌Computing‌‌versus‌‌"Hard"‌‌computing‌ CO1‌‌ ‌

3‌ ‌ Characteristics‌ ‌of‌ ‌Soft‌ ‌computing,‌ ‌Some‌ CO1,‌‌CO6‌ ‌

applications‌‌of‌‌Soft‌‌computing‌‌techniques‌ ‌
4‌ ‌ Introduction‌‌to‌‌Fuzzy‌‌logic,‌‌Fuzzy‌‌sets‌‌and‌‌ CO2‌ ‌
membership‌‌functions‌ ‌
5‌ ‌ Operations‌ ‌on‌ ‌Fuzzy‌ ‌sets.‌ ‌Fuzzy‌ ‌relations,‌ CO2‌ ‌
rules,‌ ‌propositions,‌ ‌implications‌ ‌and‌
inferences.‌ ‌
 6‌ ‌ Defuzzification‌ ‌techniques,‌ ‌Fuzzy‌ ‌logic‌ CO2‌ ‌
controller‌ ‌design,‌ ‌Some‌ ‌real‌ ‌life‌ ‌societal‌
applications‌‌of‌‌Fuzzy‌‌logic.‌ ‌
7‌ ‌ Fuzzy‌‌Inference‌‌Systems,‌ Different‌ ‌Fuzzy‌ CO3‌ ‌
Models:‌Mamdani‌ ‌Fuzzy‌ ‌Models,‌
Sugeno‌‌Fuzzy‌‌Models‌ ‌
8‌ ‌ Tsukamoto‌‌Fuzzy‌‌Models,‌‌Input‌‌Space‌‌ CO3‌ ‌
Partitioning‌‌and‌‌Fuzzy‌‌Modeling.‌‌ ‌
9‌ ‌ Neuro‌ Fuzzy‌ Modelling:‌‌Adaptive‌‌ CO3‌ ‌
Neuro-Fuzzy‌ ‌Inference‌‌Systems,‌‌
Architecture,‌‌Hybrid‌ ‌Learning‌‌
Algorithm,‌‌Learning‌ ‌Method‌‌that‌ ‌Cross-‌‌
fertilize‌ ‌ANFIS‌ ‌and‌‌RBFN‌ ‌
10‌ ‌ Concept‌ ‌of‌ ‌"Genetics"‌‌and‌‌"Evolution"‌‌and‌ CO4‌ ‌
its‌ ‌application‌ ‌to‌ ‌probabilistic‌ ‌search‌
techniques‌ ‌
11‌ ‌ Basic‌ ‌GA‌ ‌framework‌ ‌and‌ ‌different‌ ‌GA‌ CO4‌ ‌
architectures,‌ ‌GA‌ ‌operators:‌ ‌Encoding,‌
Crossover,‌‌Selection,‌‌Mutation,‌‌ ‌
Solving‌ ‌single-objective‌ ‌optimization‌
problems‌ ‌
12‌ ‌ Swarm‌ ‌Optimization:‌ ‌Introduction‌ ‌to‌ ‌Ant‌ CO4‌ ‌
Colony‌ ‌Optimization,‌ ‌Particle‌ ‌Swarm‌
Optimization‌‌etc.‌ ‌
13‌ ‌ Elementary‌ ‌applications‌ ‌in‌ ‌image‌ CO5‌ ‌
processing,‌ ‌
14‌ ‌ Pattern‌‌recognition‌ ‌ CO5‌ ‌

15‌ ‌ Designing‌‌control‌‌systems‌ ‌ CO5‌ ‌

16‌ ‌ ‌ ‌

Evaluation‌‌ GRADING‌:‌‌Test‌‌#1‌‌-‌‌25%,‌‌Test‌‌#2‌‌-‌‌25%,‌‌Homework‌‌&‌‌Lab‌‌Exercises‌‌-‌‌25%,‌‌Project‌‌-‌‌
Scheme‌ ‌ 25%‌ ‌

Minimum‌‌Pass‌‌marks:‌‌50%‌ ‌

Faculty‌‌office‌‌hours‌‌for‌‌students: ‌‌Monday‌‌15:00‌‌–‌‌17:00‌ ‌

Text‌‌Books‌ ‌ 1.‌‌George‌‌J.‌‌Klir‌‌and‌‌Bo‌‌Yuan,‌‌"Fuzzy‌‌sets‌‌and‌‌Fuzzy‌‌Logic",‌‌Prentice‌‌Hall,‌‌USA.‌ ‌
2.‌ ‌Goldberg‌ ‌D.E.,‌ ‌Genetic‌ ‌Algorithms‌ ‌in‌ ‌Search,‌ ‌Optimization,‌ ‌and‌ ‌Machine‌ ‌Learning‌
Addison‌‌Wesley.‌ ‌

3.‌ ‌Timothy‌‌J.‌‌Ross,‌‌"Fuzzy‌‌Logic‌‌with‌‌Engineering‌‌Applications",‌‌McGraw‌‌Hill‌ ‌

Other‌‌ 1. Jang‌ ‌J.S.R.,‌ ‌Sun‌ ‌C.T.‌ ‌and‌ ‌Mizutani‌ ‌E,‌ ‌"Neuro-Fuzzy‌ ‌and‌ ‌Soft‌ ‌computing",‌ ‌Prentice‌
Reference‌ ‌ Hall.‌ ‌

2.‌ ‌An‌‌Introduction‌‌to‌‌Genetic‌‌Algorithms,‌‌Melanie‌‌Mitchell,‌‌MIT‌‌Press,‌‌2000.‌ ‌
3.‌ ‌Genetic‌‌Algorithms‌‌In‌‌Search,‌‌Optimization‌‌And‌‌Machine‌‌Learning,‌‌David‌‌E.‌‌ ‌
‌Goldberg,‌‌Pearson‌‌Education,‌‌2002.‌ ‌
4.‌ ‌Practical‌ ‌Genetic‌ ‌Algorithms,‌ ‌Randy‌ ‌L.‌ ‌Haupt‌ ‌and‌ ‌sue‌ ‌Ellen‌ ‌Haupt,‌ ‌John‌ ‌Willey‌ ‌&‌
Sons,‌‌2002‌ ‌