GYAN VIHAR SCHOOL OF ENGINEERING & TECHNOLOY M.TECH ARTIFICIAL INTELLIGENCE – 2 YEARS PROGRAM

vinegarclothΤεχνίτη Νοημοσύνη και Ρομποτική

17 Ιουλ 2012 (πριν από 5 χρόνια και 3 μήνες)

722 εμφανίσεις

GYAN VIHAR SCHOOL OF ENGINEERING & TECHNOLOY

M.TECH
.
ARTIFICIAL INTELLIGENCE


2 YEARS PROGRAM


M.Tech. Artificial Intelligence

is a two
-
year (four semesters) post graduation Degree program in artificial
intelligence. The course has been designed to meet t
he growing demand for qualified professionals in the field of
Artificial Intelligence. It is a post
-
graduate course that can be taken up after obtaining graduation degree.


The Curricula and Syllabi of
M.Tech. Artificial Intelligence

course offered by Sure
sh GyanVihar University is
designed considering the need of different Software Houses in India and abroad and has a high job potential in all
the areas.


i) Need, objectives and main features of the
M.Tech. Artificial Intelligence

curriculum

Need:



To crea
te awareness among students about the central problem of
AI
characterized by Deduction,
reasoning, problem solving, Knowledge representation, Planning, Learning, Natural language processing,
Motion and manipulation, Perception, Social intelligence, Creativ
ity & General intelligence.



To provide knowledge to the students about
AI

approaches which includes Cybernetics and brain
simulation, Symbolic, Sub
-
symbolic & Statistical and various ways of integrating these approaches.



To enrich the students with case st
udies covering various complex problem solving
AI

tools like Search
and optimization, Logic, Probabilistic methods for uncertain reasoning, Classifiers and statistical learning
methods, Neural networks, Control theory & Languages.



To develop a general appr
eciation among the students of the goals, subareas, achievements and
difficulties of
AI
.



To create general understanding among the students regarding the major concepts and approaches in
knowledge representation, planning, learning, robotics and other AI a
reas.



To develop programming skills in students for
AI

applications.



To provide exposure to the students related to logic programming with practical topics.



To obtain and generate an employment in computing field.

Objectives:

The central objective of
M.Te
ch. Artificial Intelligence

course is to give a broad overview of
AI
tools and
techniques which make the students aware so that they may choose the correct AI techniques for the situation /
problems that may arise.
This advanced program is designed to give

the students thorough knowledge about
various areas of
AI
. The program intends to create a sense of awareness and understanding by including practical
ideas about
specialized AI projects
in the area of Brain Simulation, Cognitive Architecture, Games, Know
ledge
and Reasoning, Motion and Manipulation, Natural Language Processing, Planning, Optimization Problem
Solving, etc. and
multipurpose AI projects

like Software Libraries, Cloud Services, etc.

Features of the
M.Tech
.
Artificial Intelligence

curriculum:



The Four semesters
M.Tech
.
Artificial Intelligence

program

is offered by the
Department of Computer
Applications
of
Suresh Gyan Vihar
University is based on the credit system and provides a student with
wide choice of specialized areas in AI.



The program
includes courses covering the core of Artificial Intelligence discipline and several electives in areas
of Robotics, Image Processing, Pattern Recognition, Natural Language Processing, Computational Intelligence,
Text Processing, Machine Learning, Human Co
mputer Interaction and Knowledge Engineering etc.



Program comprises of several core and elective courses and project work.



Program contains job oriented and advanced practical labs.



This program contains the best combination of various computing technolog
ies.



It is the most dynamic program and provides foundation for research.



Compulsion to publish research papers in repute journals makes this program more effective and research oriented.

ii) Role of
M.Tech
.
Artificial Intelligence

curriculum in the Natio
nal development



Now
-
a
-
days, applications developed in Artificial Intelligence is being used as automated tools and advanced
techniques for problem solving are being developed in almost all the major areas like banking, medical
services, defense organizatio
ns, industrial units, stock industry, education, R & D organizations,
entertainment and gaming, etc. which plays an important role in economical, technical, statistical,
technological, logical development of the country. The
M.Tech
.

Artificial Intelligenc
e

curriculum plays an
important role in the development of graduates who can offer world class services and take the nation
forward. Also, due to the present outsourcing boom in the country, the application of computers has
increased exponentially generati
ng employment for a large section of the population.

iii) Global trends reflected in
M.Tech
.
Artificial Intelligence

curriculum



The research and development in the field of artificial intelligence is still in its infancy phase and lots of
work is being don
e in the related areas. Since the applications, tools and techniques developed using various
related areas of Artificial Intelligence finds place in all the major areas hence it generates a need for skilled
professionals globally. The Department of Compute
r Applications aims to produce high quality Post
-
Graduates in Artificial Intelligence with a sound theoretical and practical knowledge and responsibility, who
can contribute effectively in the progress
on a
local

as well as
on a global scale.


iv) Possib
ility of motivation and self development:

There are various possibilities of motivation and self development of the students through this curriculum. The
curriculum has been so designed that a student can:




Understand the professional / industry environmen
t



Understand team work and Group Dynamics.



Develop a sense of effective Problem Solving and Decision making.



Able to design, implement and test AI applications.



Develop a research oriented approach in AI application development



Think and develop projects

independently.




Develop career as AI professional.


v) Placement Opportunity:

Advancement in the field of computer science and related technologies has open up whole new opportunities in
the field of Artificial Intelligence with job ranging from manageria
l to technical. Aspiring candidates can seek
stable career as statistical analysts, programmers, language experts, engineers and managers, engineering
technicians, robotics engineers, designing software and hardware, professors and researchers. A Masters
degree in
Artificial Intelligence provides a a strong foundation for working in key positions in high
-
tech and knowledge
-
intensive research centres.



Some of the areas / sectors where AI based approaches are used are as follows:
-




Banking



Transportation



Medicine & Services



Industry and Robotics



Investigation Agencies



Space Research



Entertainment & Gaming



Education



Tourism



R & D Organizations



Pharmaceuticals Industries



Defense Organizations



Web Industry



Stock Trading



Share Trading



Investment Agencies



Law

and many more…



Some of the openings in AI and related field are as follows:
-




Data Mining Analyst



Software Development Engineer



Senior Software Engineer



Quantitative Researcher



Technical Team Lead



Knowledge Management Expert



Data Mining Coder



Technical

Writer



Data Mining Engineer



Research Scientist



Data Scientist



Data Analyst Specialist



Technical Support Manager



Algorithmin Quantitative Scientist



Systems Enginner



Research Programmer



Research Analyst



Data Decision Scientist



Research Associate



Machine Lea
rning Engineer



Lead Application Developer



Search Engine Marketing



Research Data Analyst



Risk Modeler



Knowledge Discovery Researcher



Planning and Scheduling Consultant



Human Mancine Interaction
Engineer



Research Coordinator



Test Automation Engineer



User Ex
perince Designers



Product Manager



Web Content Writers



AI Animator



Network Sceintist



Acquisition Editor



Accounts Manager


and many more…


Some of the offshore companies / corporations / organizations are estimated to offer a salary
ranging from $ 40,000 to

$ 1,50,000+ pa. The names of some of them are as follows:
-



Amazon.com



American Express



Philips



Google Inc.



Vodafone



Shell



Getronics



eBay



Baker Hughes



BP



Scribd



Deloitte
-

United States



SoftScript, Santa Monica, CA



Qualcomm, California
-

San Diego



Cl
earedConnections
-

Fort Belvoir, VA



Military Stars
-

Santa Monica, CA



Prevailance, Inc.
-

Washington, DC



Argon ST
-

Fairfax, VA



Eka Finance


Connecticut



Cameron
-

Odessa, TX



Laurus Strategies
-

Midland, MI



MerchantCircle, Inc.
-

Los Altos, CA



Stealth Star
tup
-

San Francisco, CA



Scanadu
-

San Francisco, CA



Industrial Defender, Foxborough, MA



IntelliGenesis LLC
-

Columbia, MD



Oregon State University
-

Corvallis, OR



National Security Agency
-

Honolulu, HI



Pearson Education
-

Centennial, CO



Altisource
-

Atlant
a, GA



SAIC
-

Columbia, MD



DCS Corporation
-

Aberdeen, MD



Red Arch Solutions
-

Fort Meade, MD



Tata Consultancy Services
-

Midland, MI



FICO
-

San Diego, CA



meebo
-

Mountain View, NY



BAE Systems
-

Burlington, MA



Boeing
-

Kent, WA



Vantage Labs LLC
-

New Hope,
PA



L
-
3 Communications
-

Orlando, FL



Locu
-

United States



Ipsos North America
-

Los Angeles, CA



Sears
-

Chicago, IL



Xerox
-

Webster, NY



BBN Technologies
-

Arlington, VA



Morfologica, Inc.
-

College Park, MD



Cubic Corporation
-

Orlando, FL



NeuStar
-

Mountain
View, CA



TriWest Healthcare Alliance
-

Phoenix, AZ



General Dynamics
-

IT
-

Herndon, VA



Massachusetts Institute of Technology
-

Cambridge, MA



Electronic Arts
-

Austin, TX
-

Orlando, FL
-

Los Angeles, CA



Investment Research, Referee Advisors
-

New York, NY



UT Health Science Center at Houston
-

Houston, TX



Odyssey Systems Consulting Group
-

United States



Universal Business Solutions
-

Fort Meade, MD



Virginia Tech (Virginia's largest university)



New York Media Software Company, Manhattan



SRI International
-

Pr
inceton, NJ
-

Menlo Park, CA


GYAN VIHAR SCHOOL OF ENGINEERING AND TECHNOLOGY

DEPARTMENT OF COMPUTER APPLICATIONS


Teaching and Examination Scheme for
M. Tech. FULL
-
TIME (Core) (
Artificial Intelligence
)

Edition 201
2




Year I









Semester


I



S.
No.

Course
Code

Course Name

Credits

Contact Hrs/Wk.

Exam

Hrs.

Weightage
(in%)

L

T/S

P

CE

ESE





A. Theory Papers















1

CP 533

Advances in Artificial Intelligence

3

3

-

-

3

30

70

2

CP 535

Problem Solving Methods

3

3

-

-

3

30

70

3

CP 537

A
pplication Designing using LISP

3

3

-

-

3

30

70

4


Elective I

3

3

-

-

3

30

70


CP 539

Image Processing and Pattern Recognition

-

-

-

-

-

-

-


CP 541

Genetic Algorithm and Applications

-

-

-

-

-

-

-


CP 543

Robotics

-

-

-

-

-

-

-

5


Open Electvie

3

3

-

-

3

30

70


HS 501

Soft Skills Training
-

I









CP 515

High Performance Scientific Computing












B. Practical & Sessional:








6

C
P

559

LISP LAB

2

-

-

3

3


60

40



C. Discipline and Extra Curricular
Activities








7

DE 501

Discipli
ne and E
xtra Curricular Activities


I

2





100






Total

1
9

1
5

0

3









Total Teaching Load

-

1
8

-

-

-

-

-




Year I









Semester


II



S.
No.

Course
Code

Course Name

Credits

Contact Hrs/Wk.

Exam

Hrs.

Weightage
(in%)

L

T/S

P

CE

ESE





A. Theory Papers















1

CP 534

Document Analysis & Recognition

3

3

-

-

3

30

70

2

CP 536

Knowledge Representation & Reasoning

3

3

-

-

3

30

70

3

CP 538

Logic Programming using Prolog

3

3

-

-

3

30

70

4


Elective II

3

3

-

-

3

30

70


CP 540

Nat
ural Language Processing

-

-

-

-

-

-

-


CP 542

Computational Intelligence

-

-

-

-

-

-

-


CP 544

Text Processing

-

-

-

-

-

-

-

5


Open Electvie

3

3

-

-

3

30

70


HS 50
2

Soft Skills Training


f
f









Cm 㔱Q

Bio f湦ormatics Com灵pi湧












B. P
ractical & Sessional:








6

C
P

560

Prolog LAB

2

-

-

3

3


60

40



C. Discipline and Extra Curricular
Activities








7

DE 50
2

Discipline and E
xtra Curricular Activities


f
f

O





100






Total

1
9

1
5

0

3









Total Teaching Load

-

1
8

-

-

-

-

-




L = Lecture


T = Tutorial




CE = Continuous Evaluation


S = Seminar


P = Practical




ESE = End Semester Examination













GYAN VIHAR SCHOOL OF ENGINEERING AND TECHNOLOGY

DEPARTMENT OF COMPUTER APPLICATIONS


Teaching and Examination Scheme fo
r
M. Tech. FULL
-
TIME (Core) (
Artificial Intelligence
)

Edition 201
2



Year II









Semester


III




S.
No.

Course
Code

Course Name

Credits

Contact Hrs/Wk.

Exam

Hrs.

Weightage
(in%)

L

T/S

P

CE

ESE





A. Theory Papers















1

CP 623

Arti
ficial Neural Network

3

3

-

-

3

30

70

2

CP 625

Data Mining for Business Intelligence

3

3

-

-

3

30

70

3


Elective III

3

3



3

30

70


CP 627

Machine Learning

-

-

-

-

-

-

-


CP 629

Knowledge Engineering and Expert Systems

-

-

-

-

-

-

-


CP 631

Human Com
puter Interaction

-

-

-

-

-

-

-

4


Open Electvie

3

3

-

-

3

30

70


HS
601

Soft Skills Training


I
II









CP
605

Information System Security











B. Practical & Sessional:








5


C
P

659

MATLab

2

-

-

3

3

60

40

6

SM 601

Seminar

5

-

-

9


5

6
0

40



C. Discipline and Extra Curricular
Activities








7

DE
6
01

Discipline and E
xtra Curricular Activities

II
I

2





100






Total

21

12

0

12









Total Teaching Load

-

2
4

-

-

-

-

-





Year II









Semester


IV



S.
No.

Course
Code

Cour
se Name

Credits

Contact
Hrs/Wk.

Exam Hrs.

Weightage
(in%)

L

T/S

P

CE

ESE





A. Practical & Sessional:















1

DI 602

M. Tech. Dissertation / Thesis

16

0

0

-

20 min./ student for
presentation


60

40



C. Discipline and Extra
Curricular A
ctivities








2

DE
602

Discipline and E
xtra Curricular
Activities




O





100






Total

1
8

0

0

-









Total Teaching Load

-

-

-

-

-

-

-



L = Lecture


T = Tutorial




CE = Continuous Evaluation


S = Seminar


P = Practical




ESE = End Se
mester Examination








GYAN VIHAR SCHOOL OF ENGINEERING AND TECHNOLOGY

ENGG. CLUSTER
-

B

LIST OF COURSES OF M. TECH.

AI


Course

Code

Course Name

Credits

Contact Hrs/Wk.

Exam Hrs.

Weightage (in%)

L

T/S

P

CE

ESE

CP 514

Bio Informatics Computing















CP 515

High Performance Scientific Computing















CP 533

Advances in Artificial Intelligence

3

3

-

-

3

30

70

CP 534

Document Analysis & Recognition

3

3

-

-

3

30

70

CP 535

Problem Solving Methods

3

3

-

-

3

30

70

CP 536

Knowled
ge Representation & Reasoning

3

3

-

-

3

30

70

CP 537

Application Designing using LISP

3

3

-

-

3

30

70

CP 538

Logic Programming using Prolog

3

3

-

-

3

30

70

CP 539

Image Processing and Pattern Recognition

-

-

-

-

-

-

-

CP 540

Natural Language Processin
g

-

-

-

-

-

-

-

CP 541

Genetic Algorithm and Applications

-

-

-

-

-

-

-

CP 542

Computational Intelligence

-

-

-

-

-

-

-

CP 543

Robotics

-

-

-

-

-

-

-

CP 544

Text Processing

-

-

-

-

-

-

-

CP 559

LISP LAB

2

-

-

3

3


60

40

CP 560

Prolog LAB

2

-

-

3

3


60

40

CP 605

Information System Security















CP 623

Artificial Neural Network

3

3

-

-

3

30

70

CP 625

Data Mining for Business Intelligence

3

3

-

-

3

30

70

CP 627

Machine Learning

-

-

-

-

-

-

-

CP 629

Knowledge Engineering and Expert System
s

-

-

-

-

-

-

-

CP 631

Human Computer Interaction

-

-

-

-

-

-

-


CP 659

MATLab

2

-

-

3

3

60

40

SM 601

Seminar

5

-

-

9


5

60

40

DI 602

M. Tech. Dissertation / Thesis

16

0

0

-

20 min./
student for
presentation


60

40

HS 501

Soft Skills Training
-

I















HS 502

Soft Skills Training


II















HS 601

Soft Skills Training


III















DE 501

Discipline and Extra Curricular Activities


I

2









100



DE 502

Discipline and Extra Curricular Activities


II

2









100



DE
601

Discipline and Extra Curricular Activities

III

2









100



DE 602

Discipline and Extra Curricular Activities


IV

2









100






L = Lecture


T = Tutorial




CE = Continuous Evaluation


S = Seminar


P = Practical




ESE = End Semester E
xamination








CP 514


BIO
-
INFORMATICS COMPUTING




C(L,T,P) = 3 (3,0,0)





Units

Course Contents

Hours


I

Introductory Concepts:
The Central Dogma


The Killer application


Parallel Universes


Watson’s
Definition


Top Down Versus Bottom up


In
formation Flow


Convergence


Databases


Data
Management


Data Life Cycle


Database Technology


Interfaces Implementation


Networks


Geographical Scope


Communication Models


Transmissions Technology


Protocols


Bandwidth


Topology


Hardware


Contents


Security


Ownership


Implementation


Management.



7


II

Search Engines and Data Visualization:
The search process


Search Engine Technology


Searching and Information
Theory


Computational methods


Search Engines and Knowledge
.
Manage
ment


Data Visualization


sequence
visualization


structure visualization


user Interface


Animation Versus simulation


General Purpose Technologies.


7


III

Statistics and Data Mining:
Statistical concepts


Microarrays


Imperfect Data


Randomnes
s

Variability


Approximation


Interface Noise


Assumptions


Sampling and Distributions


Hypothesis Testing


Quantifying Randomness


Data Analysis


Tool selection statistics of Alignment


Clustering and
Classification


Data Mining


Methods


Sel
ection and Sampling


Preprocessing and Cleaning


Transformation and Reduction


Data Mining Methods


Evaluation


Visualization


Designing new queries


Pattern Recognition and Discovery


Machine Learning


Text Mining


Tools.
\


7


IV

Pattern Matchi
ng:
Pairwise sequence alignment


Local versus global alignment


Multiple sequence alignment


Computational methods


Dot Matrix analysis


Substitution matrices


Dynamic Programming


Word methods


Bayesian methods


Multiple sequence alignment


Dyna
mic Programming


Progressive strategies


Iterative
strategies


Tools


Nucleotide Pattern Matching


Polypeptide pattern matching


Utilities


Sequence Databases.

8


V

Modeling and Simulation:
Drug Discovery


Components


Process


Perspectives


Num
eric considerations


Algorithms


Hardware


Issues


Protein structure


AbInitio Methods


Heuristic methods


Systems Biology


Tools

6


Total

35

REFERENCE BOOKS:

1.

Ranjan Bose, “Information Theory, Coding and Cryptography”, Tata Mc
Graw
-

Hill, 2002.

2.

Viterbi, “Information Theory and Coding”, McGraw
-
Hill, 1982.

3.

John G. Proakis, “Digital Communications”, McGraw
-
Hill, New edition, 2000.

4.

Gareth A. Jones and J. Mary Jones, “Information and Coding Theory”, Springer

Undergraduate

Mathematics Series, 2000





CP 515


HIGH PERFORMANCE SCIENTIFIC COMPUTING



C(L,T,P) = 3 (3,0,0)



Units

Course Contents

Hours

I

Overview of Scientific Computing, Tools
-
Elements of Mat Lab, Elements of IDL, Elements of AVS,

7

II

Scientific Visualizati
on Architecture
-

Computer Performance. Vector Computing.

7

III

Distributed
-
memory MIMD Computing. SIMD Computing.

8

IV

Applications
-
Advection. Computerized Tomography.

8

V

A review of selected topic from Numerical Analysis.

7


Total

3
7

REFERENCE BOOKS:

1 G.H. Golub,J.M. Ortega"Scientific computing
-
An introduction With parallel computing" Academic Press,

2. Lloyd D. Fosdick,Elizabeth R. Jessup,Carolyn"an introduction to High Performance Scientific computing" PHI




CP 533


ADVANCES
IN ARTIFICIAL INTELLIGENCE


C(L,T,P) = 3 (3,0,0)



Units

Contents of the course

Hours

1

Introduction: AI problems, foundation of AI and history of AI intelligent agents: Agents and Environments, the
concept of rationality, the nature of environments, stru
cture of agents, problem solving agents, problem formulation.

7

2

Knowledge Representation & Reasons logical Agents, Knowledge


Based Agents, logic, propositional logic,
Resolution patterns in propositional logic, Resolution, Forward & Backward. Chaining
.

6

3

Propositional Vs. first order inference, unification & lifts forward chaining, Backward chaining, Resolution.

7

4


Advances in Artificial Intelligence: Cybernetics, Brain Simulation, Cognitive Systems

8

5

Social Intelligence, Introduction to AI ba
sed programming Tools, Robotics.

7


Total

35

Reference Books:

1.

Artificial Intelligence


A Modern Approach. Second Edition, Stuart Russel, Peter Norvig, PHI/ Pearson Education.

2.

Artificial Neural Networks B. Yagna Narayana, PHI

3.

Artificial Intelligence , 2n
d Edition, E.Rich and K.Knight (TMH).

4.

Artificial Intelligence and Expert Systems


Patterson PHI.

5.

Expert Systems: Principles and Programming
-

Fourth Edn, Giarrantana/ Riley, Thomson.

6.

PROLOG Programming for Artificial Intelligence. Ivan Bratka
-

Third Editio
n


Pearson Education.

7.

Neural Networks Simon Haykin PHI

8.

Artificial Intelligence, 3rd Edition, Patrick Henry Winston., Pearson Edition.





C
P

5
3
4



DOCUMENT ANALYSIS AND RECOGNITION C(L,T,P) = 3 (3,0,0)

Units

Contents

Hours

1

Introdu
ction to documents and processing: Introduction; to documents and models of document processing, top
-
down, bottom up approaches, document understanding approaches, image extraction and foreground background
separation, layout analysis, text and graphics se
paration, form document processing.

7

2

Classification Principles: Patterns and feature vectors, Bayesian classification, clustering, neural classifiers, other
classifiers, including string and edit distances.

7

3

Optical Character Recognition: Categori
es of text, printed and handwriting, printed fixed and variable font methods,
numeral recognition of hand
-
written cursive scripts, holistic and analytic methods.

7

4


Graphics Recognition Methods: Region segmentation, vectorization, feature extraction, g
raphics recognition and
interpretation. Tools and Techniques: Statistical PR Lib, OCR Software

7

5

Image Processing Library Applications: Various applications and Scripts, multi lingual form analysis, Forensic
document examination: examining signatures, h
andwriting, obliterations erasures and overwriting etc.,

7


Total

35

Reference Books
:

1.

Duda and Hart: " Pattern Classification and Scene Analysis", J.Wiley and Sons.

2.

Earl Gose et al: "Pattern Recognition and Image Analysis", Prentice Hall of India, New De
lhi, 1998.

3.

Baird, Bunke and Yamamoto. (Eds): "Structured Document Image Analysis", Chapters on understanding of printed documents and gr
aphics
recognition. Springer Verlag 1992.

4.

L. O'Gorman and R.Kasturi: "Document Image Analysis: An Executive Briefing",
IEEE Computer Society Press 1998.

5.

H. Bunke and P. S. P. Wang (Eds.): "Handbook of Character Recognition and Document Image Analysis" World Scientific Press, Si
ngapore 1997.

6.

E. G. Mallach, “Decision Support and Data Warehouse Systems", Tata McGraw Hill.

7.

Mic
hael Berry and Gordon Linoff “Mastering Data Mining
-

Art & science of CRM”, Wiley Student Edition


CP

535


PROBLEM SOLVING METHODS



C(L,T,P) = 3 (3,0,0)

Units

Contents

Hours

1

General introduction of AI, Intelligent systems etc, AI Applications

7

2

Sea
rch techniques, single
-
agent path
-
finding problem, two player game, interleaving search

6

3

Constraint satisfaction problems

7

4

Logic, modus ponens, Satisfiability, Resolution, Refutation, Unification

8

5

AI Planning, Distributed AI

7


Total

35

Refe
rence Books:

1. N.J.Nilsson: Principles of Artificial Intelligence, Narosa Publications.

2. D. W. Patterson: Introduction to AI & Expert System, PHI.

3. S. Russell and P. Norvig. AI: A Modern Approach, 2nd Edn., McGraw
-
Hill, 2003.


C
P

5
3
6

KNOWLEDGE PEPRE
SENTATION & REASONING

C(L,T,P) = 3(
3,0,0)

Units

Contents

Hours

1

Survey of Representation techniques: representation schemes: Logic: Procedural representations: Semantic
networks: Conceptual structures

7

2

Production systems: Analogical representation:
Semantics primitives: Frames and Scripts: conceptual
Dependency: Applications of Knowledge Representation

8

3

Languages, Syntax and well
-
formed formulas (wffs), Semantics, Properties of Wffs. Formal deduction Inference
Rules, Logical Axioms, Formal Proof
s, Theories and Theorem Proving Lowentheim
-
skolem Theorems

7

4


Classical first order logics
-
Propositional logic, Predicate Calculus. Non
-
classical Logics and their application
to knowledge representation and processing.

6

5

Brief Introduction
-

Many sor
ted Logics, Non
-
monatomic Logics, Multi
-
valued Logics, Fuzzy Logic, Model
Logic, Temporal Logic, Intentional Logic.

6


Total

35

Reference Books
:

1.

Knowledge Representation and Reasoning by Ronald Brachman and Hector Levesque, Morgan Kaufmann Publishers

2.

L
ogic Programming, Knowledge Representation, and Nonmonotonic Reasoning by Michael Gelfond, 1st Edition, 2011,

3.

XIII, 513 p.p, Springer.

4.

Knowledge Representation, Reasoning and Declarative Problem Solving by Alex M. Andrew, Kybernetes, Vol. 33 Issue:1,Emer
ald Group

Publishing Limited

CP 53
7


APPLICATION DESIGNING USING LISP


C(L,T,P) = 3 (3,0,0)

Units

Contents of the course

Hours

1

Introduction and scope of LISP, Flow of control: function calls, recursion, iteration, conditionals,
LISP map functions.

7

2

Data structures: lists, generalized sequences, association lists, properties, sets, trees, stacks, hash
tables, characters, strings.

6

3

Variables: local and global scope, control of parameters, optional parameters, lambda var
iables.

7

4

Lambda forms, Macros, LISP internal representation.

8

5

Problem decomposition, data abstraction, debugging, program development.

7


Total

35

Reference Books:

1.

Common Lisp: The Language by Guy Steele, Digital Press

2.

Common Lisp: A Gentle Intro
duction to Symbolic Computation by David S. Touretzky, Symbolic Technology Ltd.

3.

On Lisp: Advanced Techniques for Common Lisp by Paul Graham




C
P

5
3
8

LOGIC PROGRAMMING USING PROLOG


C(L,T,P) = 3 (3,0,0)


Units

Contents of the course


Hours

1

Preposit
ional logic: syntax and semantics: Validity and consequence. Normal forms. Representing
world knowledge using prepositional logic.

7

2

First order logic: World knowledge representation and the need for quantifiers. Syntax, semantics
validity consequence c
lause normal from

8

3

Introduction to prolog: Syntax of prolog, Structured data representation. Execution model
Introduction to Programming in Prolog, Illustrative examples

6

4

The connection between logic and logic programming interpreting logic program
s in terms of Horn
clauses Deduction from clause form formulas resolution for prepositional logic Ground resolution.
Unification and first order resolution SLD resolution; the computation and search rules. SLD trees
and interpretation of


non
-
declarative f
eatures of Prolog.

7

5

Advanced prolog features: programming techniques: Structural Induction and Recursion, Extra
Logical features: Cut and Negation Case studies.

7


Total

35

Reference Books
:

1.

Stoll, set Theory and logic, Dover publishers, New York, 196
3.

2.

Clocksin, W.F. and Mellish, C.S., Programming in Prolog 2nd edition, Springer
-
Verlag, 1984

3.

Gries, The Science of Programming, Narosa Publishers, 1985

4.

O’ Keefe, R., The Craft of Prolog. The MIT Press, 1991.

5.

Lloyd, J. W., Foundation of Logic Programming,

Springer, 1984.


CA
539

IMAGE PROCESSING & PATTERN
RECOGNITION


C(L,T,P) = 3 (3,0,0)


Units

Contents

Hours

1

INTRODUCTION:
Imaging in ultraviolet and visible band. Fundamental steps in image
processing. Components in image processing. Image perception in

eye, light and electromagnetic
spectrum, Image sensing and acquisition using sensor array.

DIGITAL IMAGE
FUNDAMENTALS: Image sampling and quantization, Representing digital images, Basic
Relationship Between Pixels, Zooming and Shrinking digital images,

7

2

INTENSITY TRANSFORMATION:

Basic Intensity transformation functions, Histogram
processing, Fundamental of Spatial Filtering. Sharpening Spatial filters.

IMAGE
RESTORATION:

Image restoration model, Noise Models, Spatial and frequency properties of
noise,

noise probability density functions, Restoration in presence of noise
-

only spatial filter,
Mean filter, order Statistic filter and Adaptive filter, Frequency domain filters
-

Band reject filter,
Band pass filter and Notch filter.

7

3

IMAGE COMPRESSION:

Compression Fundamentals
-

Coding Redundancy, Interpixel redundancy,
Psycho visual redundancy and Fidelity criteria. Image Compression models, Source encoder and
decoder, Channel encoder and decoder, Lossy compression and compression standards.

8

4

IMAGE

SEGMENTATION:

Fundamentals, point , edge and line detection., Threshold
ing
,
Region based segmentation., Region based segmentation, Region Growing & Splitting & merging.

6

5

EXPERT SYSTEM AND PATTERN RECOGNITION:

Use of computers in problem solving,
infor
mation representation, searching, theorem proving, and pattern matching with substitution.
Methods for knowledge representation, searching, spatial, temporal and common sense reasoning,
and logic and probabilistic inference. Applications in expert systems
and robotics.

7


Total

35

Reference Books
:

1. Duda R O and P E Hart, Patten classification and scene analysis, John Wiley & Sons, NY 1973

2. K.S.Fu, Syntactic pattern recognition and applications, Prentice Hall, NJ, 1982

3. T.Pavlidis, Structural pattern

recognition, Springer
-
Verlag, NY, 1977

4. D.H.Ballad and C.M.Brown, Algorithms for computer vision, Prentice Hall, 1982

5. R.Schalkoff, Pattern Recognition: Statistical, Structural and Neural Approaches, John Wiley & Sons, NY, 1992.

6. Digital Image Proc
essing : Gonzalez & Wood, Addison
-
Wisley Publisher Comp. 1993.

7. Digital Image Processing : A.K Jain, PHI, Edition 1995.


C
P

5
4
0


NATURAL LANGUAGE PROCESSING



C(L,T,P) = 3 (3,0,0)


Units

Contents

Hours

1

Introduction: Knowledge in speech and language p
rocessing


Ambi杵ity


jo摥ls and
Al杯rithms


ian杵a来I qho畧桴 a湤nrn摥rsta湤n湧n oe杵gar bxpressions an搠a畴omataW oe杵ga爠
e硰xessions


cinite
J
ptate a畴omataK
Morphology and Finite
-
State Transducers: Finite
-
State
Morphological parsing


Combining FST
lexicon and rules

6

2

Word classes and part
-
of
-
speech tagging: English word classes


qa杳ets for bnglish


ma牴
J

J
s灥ech ta杧g湧n


o畬e
J
base搠 灡rt
J

J
s灥ech ta杧g湧n


ptochastic 灡牴
J

J
s灥ech ta杧in朠


qransformation
J
base搠tag杩n朠


lther iss略sK 䍯nte

J
cree d牡mmars for b湧nishW 䍯nstit略ncy


䍯nte硴
J
cree 牵res an搠trees


pentence
J
le癥l constr畣tions


qhe no畮 p桲ase


䍯or摩湡tion


A杲eement


qhe verb 灨pse an搠s畢 cate杯rization


Au硩lia物es


p灯步n la湧畡来 synta砠


d牡mmars e煵qvalence and
no牭al



P

ceatures a湤n rnificationW ceature str畣tures


rnification of 晥at畲e str畣tures


ceatures
st牵rtures in the grammar


fmpleme湴i湧nunification


marsin朠with u湩fication const牡i湴s


qypes and f湨eritanceK ie硩calize搠and mrobabilistic mar
singW mrobabilistic conte硴
J
free gramma爠


灲oblems with m䍆ds


mrobabilistic le硩calize搠 䍆ds


ae灥n摥ncy drammars


e畭a渠
灡rsingK



Q

oe灲esentin朠 jea湩ngW 䍯m灵tatio湡l 摥si摥rata for represe湴ations


jea湩n朠 str畣ture o映
lan杵a来


cirst or摥r pr
e摩cate calc畬畳


pome ling畩stically releva湴 conce灴s


oelate搠
representatio湡l a灰roaches


Alte牮rtive a灰roaches to meani湧n pema湴ic A湡lysisW pyntax
J
arive渠sema湴ic a湡lysis
K



R

tor搠 pense aisambi杵gtion an搠 fnformation oet物evalW pelectional r
estriction
J
base搠
摩sambi杵atio渠


oob畳t wor搠sense 摩sambi杵ation


fnformation ret物eval


other informatio渠
ret物eval tas歳K katural ian杵a来 denerationW f湴ro摵dtion to lan杵a来 来neration


Architect畲e
景r 来neration


purface realization


aisco畲se

灬a湮nn朠


lther iss略sK jachine q牡nslationW
iang畡来 simila物ties an搠 dif晥rences


qhe t牡nsfer metaphor


qhe interlin杵a i摥aW rsi湧
meani湧n


airect translation


rsing statistical tec桮i煵qs


rsability an搠system 摥癥lo灭entK

U


Total

4
5

Referen
ce Books:

1.

James Allen: Natural Language Understanding, The Benjamin/Cummings Publishing Co, Inc.

2.

Eugene Cherniak: Statistical Language Learning, MIT Press, 1993.

3.

Michael P. Oakes: Statistics for Corpus Linguistics, Edinburgh University Press, 1998.

4.

Daniel
Jurafsky & James H.Martin, “ Speech and Language Processing”, Pearson Education (Singapore) Pte. Ltd., 2002.

5.

James Allen, “Natural Language Understanding”, Pearson Education, 2003.



CA 541


GENETIC ALGORITHMS AND APPLICATIONS

C(L,T,P) = 3 (3,0,0)


Unit
s

Contents

H
ours

1

INTRODUCTION TO EVOLUTIONARY COMPUTATION

:
Biological and artificial
evolution


Evolutionary computation and AI


Different historical branches of EC
-
GAs
-

EP
-

ES
-

GP
-

A simple evolutionary algorithm.

7

2

SEARCH AND SELECTION OPERATO
RS
:
Recombination/Crossover for strings
-

one
-
point
-

multi
-

oint
-
uniform crossover

operators
-

Mutation for strings
-

bit
-
flipping


Recombination

/

Crossover and

mutation rates
-

Recombination for real
-
valued representations
-

Fitness

proportional selection

and fitness scaling


Ranking methods


Tournament

selection.

8

3

EVOLUTIONARY COMBINATORIAL OPTIMIZATION
:
TSP
-

Evolutionary algorithms for
TSPs


Hybrid evolutionary and local search

algorithms. Schema theorems
-

Convergence of EAs
-

Computational time

complexity of EAs
-

No free lunch theorem.

6

4

CONSTRAINT HANDLING
:
Common techniques
-

penalty methods
-

repair methods
-

Analysis

Some

examples.

Pareto optimality
-

Multiobjective evolutionary algorithms.

7

5

GENETIC PROGRAMMING
:
Trees as individuals
-

Major steps of genetic programming
-
,
functional and

terminal sets
-

initialization
-

crossover
-
mutation
-

fitness evaluation
-

Search

operators on trees


Examples.

7


Total

35

Reference Books
:

1.

Goldberg and David E, "Genetic Algorithms in Search. Optimiza
tion and Machine Learning", Pearson Education,

New Delhi, 2006.

2.

Kalyamoy Deb, "Multiobjective Optimization using Evolutionary Algorithms", John Wiley & Sons, First Edition, USA, 2003.

`



C
P

5
4
2


COMPUTATIONAL INTELLIGENCE


C(L,T,P) = 3 (3,0,0)


Units

Contents

H
ours

1

Introduction to Computational Intelligence / Soft computing: Soft versus Hard Computing, Various
paradigms of computing, Foundations of Biological Neural Networks: Introduction to Neural
Networks, Humans and Computers, Organization of th
e Brain, Biological Neuron, Biological and
Artificial Neuron Models, Hodgkin
-
Huxley, Neuron Model, Integrate
-
and
-
Fire Neuron Model,
Spiking Neuron Model,

8

2

Introduction to Neural Networks, Humans and Computers, Organization of the Brain, Biological
Neur
on, Biological and Artificial Neuron Models, Hodgkin
-
Huxley, Neuron Model, Integrate
-
and
-
Fire Neuron Model, Spiking Neuron Model, Characteristics of ANN(Learning, Generalization,
Memory, Abstraction, Applications), McCulloch
-
Pitts Model, Historical

Develop
ments Essentials
of Artificial Neural Networks: Introduction, Artificial Neuron Model,

7

3

Operations of Artificial Neuron, Types of Neuron Activation Function, ANN Architectures,
Classification Taxonomy of ANN

Co湮ectivity ⡆ee搠景rwar搬 feedbac欬 pingl
e a湤nj畬ti
J
laye爠
ke畲al aynamics ⡁ctivation a湤n pynaptic⤬ iea牮i湧n pt牡te杹 ⡓異urvise搬 rns異urvise搬
oeinforcement⤬ iea牮rng o畬es ⡅牲or 䍯牲ectio測 ee扢ia測 䍯m灥titiveI ptoc桡sticFI

T

Q

qypes 潦 A灰pication ⡐atte牮 ClassificationI matte牮 Cl畳te
ringI matte牮 Association L jemoryI
c畮ction A灰ro硩matio測 mre摩ctionI lptimization⤠ ke畲ul Architectures with p異urvised
iea牮i湧n pi湧ne iayer cee搠corwar搠keural ketwor歳 ⡐erce灴ron⤬ j畬tilayer cee搠景rward
ke畲al ketwor歳 ⡂ac歰ko灡条tion lea牮i湧nI

oa摩al Basisc畮ction ketwor歳I p異灯rt secto爠
jac桩nesI pim畬ate搠 A湮ealin本 Boltzma湮 jac桩neI ceedbac欠 ⡒ec畲ue湴⤠ ketwor歳 and
aynamical pystems Associative jemoriesW jatrix memoriesI Bi摩rectional Associative jemory

S

R

Basic conce灴sI f畺zy set theo
ryI basic operationsI f畺zificatio測 摥f畺zificationI neurof畺zy
a灰roac栬 a灰lications bvol畴io湡ry and denetic Al杯rit桭sW Basic conce灴s of e癯l畴ionary
com灵pin本 来netic o灥ratorsI fitness f畮ction an搠selectio測 来netic programmingI other mo摥ls 潦o
e
癯l畴ion and lea牮rngI ant

T


Total

35

Reference Books:

1.

Andonie, R., Cataron, A.
Computational Intelligence

(in Romanian), Transylvania University Press, Brasov, Romania, 2002.

2.

Zurada, J.
Introduction to Artificial Neural Systems
. West Publishing Compan
y, St. Paul, 1992.

3.

Haykin, S.
Neural Networks
-

A Comprehensive Foundation
. Macmillan College Publishing Company, New York, 1999 (second
edition).

4.

M. T. Hagan, H. B. Demuth, M. Beale,
Neural Network Design
, PWS Publishing Co., Boston, 1996.

5.

Rao, V.
C++
Neural Networks and Fuzzy Logic
, M&T Books, IDG Books Worldwide
.


C
P

5
43



ROBOTICS


C(L,T,P) = 3 (3,0,0)



Units

Contents

H
ours

1

Definition and classification of ROBOTS and manipulators, motion a
nd degrees of freedom,
motion categorie
s, uses, field of applications.

7

2

Robot Arm Kinematics: Direct and Inverse, Robot arm dynamics, Manipulator trajectories, control
of robot manipulators. Introduction to sensing and vision in robotics.

8

3

Trajecto
ry Generation: Introduction, general considerations in path description and generation,
joint space schemes, Cartesian space schemes, Path generation in runtime, Planning path using
dynamic model.

6

4

Linear control of manipulators: Introduction, feedback

and closed loop control, second order linear
systems, control of second
-
order systems, Trajectory following control, modeling and control of a
single joint.

7

5

Robot Programming languages & systems: Introduction, the three level of robot programming,
re
quirements of a robot programming language, problems peculiar to robot programming
languages.

7


Total

35

Reference Books
:

1.

John J. Craig, “Introduction to Robotics”, Addison Wesley publication

2.

Richard D. Klafter, Thomas A. Chmielewski, Michael Negin, “Ro
botic Engineering


An integrated approach”, PHI Publication

3.

Tsuneo Yoshikawa, “Foundations of Robotics”, PHI Publication

4.

B. K. P. Horn,
Robot Vision,

MIT Press, Cambridge,1986.

5.

J. J. Craig,
Introduction to Robotics
, Addision
-
Wesley,1989.

6.

Y. Koren,
Robotic
s for Engineers
, MsGraw Hill,1985.








C
P

5
4
4



TEXT PROCESSING




C(L,T,P) = 3 (3,0,0)


Units

Contents

H
ours

I

String Processing
-

Efficient techniques for string processing. String searching algorithms
-

Knuth
-

Morris
-
Pratt, Boyer
-
Moore and Rabin
-
Karp algorithms. Processing binary strings. Incremental
search techniques. Pattern Matching
-

Regular Expressions, regular grammars, deterministic and
nondeterministic finite state machines for pattern matching.

8

II

Corpus Analysis
-

Corpus creation. St
orage and indexing techniques. Morpheme, word and
sentence level statistics. Zipf's law. Corpus indexing techniques. Word and sentence level n
-
grams.
Analysis for Hidden Morkov models. Text tagging.

Computational Techniques in Lexicography
-

From corpus to

lexicon. Lexical knowledge bases
-

Electronic dictionaries and thesauri. Efficient
storage and retrieval
-

B
-
Trees, TRIE, and Hashing.Dictionary analysis tools.

8

III

Text layout
-

Justification, placement of figures, equations, etc.

:
Paragraph and page

formatting.
Table of Contents, Index, and Bibliography creation. Footnotes and cross references. Spell
Checking, Grammar Checking and Style Checking
-

Statistical and linguistic approaches to better
writing tools. Isolated and context dependent spell and
grammar checking tools

6

IV


Introduction to Grammars and Parsers. Active Chart Parsing. Acceptance based, Relaxation based
and Expectation based techniques. Multi
-
Script and Multi
-
lingual text processing
-

Scripts and
Fonts
-

Multi
-

Script processing and

GIST technology. Fonts and font libraries. Bilingual and
Multi
-
lingual dictionaries, thesauri and word processors.

6

V

Cryptology
-

Techniques for text encryption and decryption. Text

Compression for efficient
storage and transmission of textual data. Ap
plications to Natural Language processing, Speech
Recognition, Optical Character Recognition, Information Retrieval and Office Automation.

7


Total

35

Reference Books
:

1. Gerald Salton, "Automatic Text Processing", Addison
-
Wesley, 1989.

2. Bran Boguraev,

Ted Briscoe (Eds), Computational Lexicography for Natural Language Processing,

Longman, 1989.

3. Robert Sedgewick, "Algorithms in C", Addison Wesley, 1990
-

4. J.E. Hopcroft and J.D.Ullman, "Automata Theory, Languages and Computation", Narosa, 1992.

5. A V

Aho, Ravi Sethi, J D Ullman, "Compilers: Principles, Techniques and Tools", Addison
-
Wesley,

1986.

6. S.N. Srihari, "Computer Text Recognition and Error Correction", IEEE Computer Soceity Press,

1984.


C
P

559

LISP LAB







C(L,T,P) = 2 (0,0,
3
)


Un
its

Contents

Hours

1.


Flow of control: function calls, recursion, iteration, conditionals, LISP map functions.

6

2.


Data structures: lists, generalized sequences, association lists, properties, sets, trees, stacks, hash
tables, characters, strings.

9

3.


Va
riables: local and global scope, control of parameters, optional parameters, lambda variables

6

4.


Lambda forms,

LISP internal representation
,

Macros

4

5.


Problem decomposition, data abstraction, debugging, program development.

4


Total

29

Sample
Exercises
:

1.

Write a LISP Program to solve the water
-
jug problem using heuristic function.

2.

Create a compound object using Turbo Prolog.

3.

Write a Prolog Program to show the advantage and disadvantage of green and red cuts.

4.

Write a prolog program to use of BEST
-
FIRST SE
ARCH applied to the eight puzzle

problem.

5.

Implementation of the problem solving strategies: Forward Chaining, Backward Chaining,

Problem Reduction.

6.

Write a Lisp Program to implement the STEEPEST
-
ASCENT HILL CLIMBING.

7.

Write a Prolog Program to implement COU
NTE PROPAGATION NETWORK.



C
P

560


PROLOG LAB




C

(L,T,P) =
2(0,0,
3
)


Units

Contents

Hours

1.


Syntax and Unification
:
Prolog's slim syntax
will be

described. Unification
will be
described with
examples to show how pattern mat
ching is achieved.

6

2.


Lists, terms and arithmetic
:

The Prolog syntax is used to create lists and terms, and to perform
simple arithmetic.

9

3.


Graphs
:

Classic graph algorithms are presented in the declarative Prolog style.

6

4.


Trees
:

Classic tree algorit
hms are presented in the declarative Prolog style.

4

5.


Difference structures
:

Difference lists are described and students participate in a re
-
write of
programs from classical lists to difference lists
.

4


Total

29

Reference Books
:

PROLOG programming for

artificial intelligence

by
Bratko
,

Addison
-
Wesley (3rd ed).




CP 605


INFORMATION SYSTEM SECURITY




C(L,T,P) = 3 (3,0,0)



Units

Course Contents

H
ours

I

Multi level model of security, Cryptography, Secret Key Cryptography, Modes of Operation, Hashes a
nd
Message Digest, Public Key Algorithm, Security Handshake Pitfall, Strong Password Protocol; Case study of
real time communication security.

7

II

Introduction to the Concepts of Security, Security Approaches, Principles of security, Types of attacks;
Cr
yptographic Techniques: Plain text and Cipher text , Substitution Techniques, Transposition Techniques
Encryption and Decryption, Symmetric and Asymmetric Key Cryptography.

8

III

Computer
-
based symmetric Key Cryptographic; Algorithms: Algorithm Types and

Modes, An Overview of
Symmetric Key Cryptography, Data Encryption Standard (DES), International Data Encryption Algorithm
(IDEA), Advanced Encryption Standard (AES); Computer
-
based Asymmetric Key Cryptographic Algorithms;
Cryptography, An Overview of Asym
metric Key Cryptography, The RSA algorithm, Symmetric and
Asymmetric Key Cryptography Together, Digital Signatures, Knapsack Algorithm.

7

IV




Public Key Infrastructure (PKI) Digital Certificates, Private Key Management, The PKI Model, Public Key
Cryptog
raphy Standards (PKCS); Internet Security Protocols Secure Socket Layer (SSL), Secure Hyper Text
Transfer Protocol (SHTTP), Time Stamping Protocol (TSP), Secure Electronic Transaction (SET), SSL versus
SET, 3
-
D Secure Protocol, Electronic Money, Email Secu
rity; User Authentication Mechanisms:
Authentication Basics, Passwords, Authentication Tokens, Certificate
-
based Authentication.

8

V


Practical Implementations of Cryptography/Security: Cryptographic Solutions Using Java, Cryptographic
Solutions Using Mic
rosoft, Cryptographic Toolkits, Security and Operating Systems; Network Security: Brief
Introduction to TCP/IP, Firewalls, IP Security, Virtual Private Networks (VPN); Case Studies on Cryptography
and Security

7


Total

37

Reference Books:

1. Atul Kahate "Cryptography and Network Security" Tata McGraw
-
Hill

2. Charlie Kaufman,Radia Perlman,Mike Speciner" Network Securities" Pearson,

3. J. A. Coopeer "Computer Communication Securities"TMH,

4. D.W. Davies W. L. Price "securities For computer N
etworks"

5. John Wiley Sons, L.Stein "Web Securities A step by step Guide " Addison Wesley.





C
P

6
2
3




ARTIFICIAL NEURAL NETWORKS


C(L,T,P) = 3 (3,0,0)


Units

Contents

Hours


1

INTRODUCTION TO ARTIFICIAL NEURAL NETWORKS :
Introduction, Artificial Neura
l Networks,
Historical Development of Neural Networks, Biological Neural Networks, Comparison Between Brain and
the Computer, Comparison Between Artificial and Biological Neural Networks, Network Architecture,
Setting the Weights, Activation Functions, Lea
rning Methods.

7


2

FUNDAMENTAL MODELS OF ARTIFICIAL NEURAL NETWORKS:
Introduction, McCulloch


Pitts
Neuron Model, Architecture, Learning Rules, Hebbian Learning Rule, Perceptron Learning Rule, Delta
Learning Rule (Windrow
-
Hoff Rule or Leastmean Squre (L
MS) rule, Competitive Learning Rule, Memory
Based Learning.

7



3

FEED FORWARD NETWORKS:
Single Layer Perceptron Architecture, Algorithm, Perception Algorithm
for Several Output Classes, Perceptron Convergence Theorem, Back Propagation Network (BPN),
Gene
ralized Delta Learning Rule, Back Propagation rule, Architecture, Training Algorithm, Selection of
Parameters, Learning in Back Propagation, Application Algorithm, Local Minima and Global Minima, Radial
Basis Function Network (RBFN).

7


4

ADALINE AND MADA
LINE NETWORKS:
Adaline Architecture, Algorithm, Applications, Madaline,
Architecture, MRI Algorithm, MRII Algorithm.

7


5

COUNTER PROPAGATION NETWORKS :
Winner Take


all learning, out star learning, Kohonen Self
organizing network, Grossberg layer Networ
k, Full Counter Propagation Network (Full CPN), Architecture,
Training Phases of Full CPN, Training Algorithm, Application Procedure, Forward Only counter Propagation
Network, Architecture, Training Algorithm, Applications, Learning Vector Quantizer (LVQ).

7


Total

35

Reference Books
:

1. Introduction to Artificial Neural Systems
-

J.M.Zurada, Jaico Publishers, 3rd Edition.

2. Introduction to Neural Networks Using MATLAB 6.0
-

S.N. Shivanandam, S. Sumati, S. N. Deepa, TMH.

4. Artificial Neural Network


Si
mon Haykin, Pearson Education, 2nd Ed.

5. Fundamental of Neural Networks


Laurene Fausett, Pearson, 1st Ed.

6. Artificial Neural Networks
-

B. Yegnanarayana, PHI.









C
P

6
2
5


DATA MINING FOR BUSINESS INTELLIGENCE



C(L,T,P)=3(3,0,0)

Units

Contents

Ho
urs


1

Data Mining
-
Definition
,
Functionalities

&

Classification
,

DM task primitives, Integration of a Data

Mining system with a Database or a Data Warehouse, Major issues in Data Mining.

Data
Warehousing (Overview Only):
Overview of concepts like star sch
ema, fact and dimension tables,
OLAP operations, From OLAP to Data Mining.

8


2

Data Preprocessing: Why? Descriptive Data Summarization, Data Cleaning: Missing Values, Noisy
Data, Data
Integration and Transformation. Data Reduction:
-
Data Cube Aggregation,

Dimensionality
reduction, Data Compression, Numerosity Reduction, Data Discretization and Concept hierarchy generation
for numerical and categorical data.

6


3

Mining Frequent Patterns, Associations, and Correlations: Market Basket Analysis, Frequent
Ite
msets, Closed Itemsets, and Association Rules, Frequent Pattern Mining,

Efficient and Scalable
Frequent Itemset Mining Methods, The Apriori Algorithm for finding Frequent Itemsets Using
Candidate Generation, Generating Association Rules
,

Mining Multilevel

Association Rules
.


8


4


Classification & Prediction
,

Issues regarding Classification and prediction
,
Classification methods
,
Cluster Analysis, Categories of clustering methods, Partitioning methods
,

Hierarchical Clustering
-
Agglomerative and Divisive Cl
ustering, BIRCH and ROCK methods, DBSCAN, Outlier Analysis

6


5

Spatial Data and Text Mining: Spatial Data Cube Construction and Spatial OLAP, Mining

Spatial
Association and Co
-
location Patterns, Spatial Clustering Methods, Spatial

Classification and Spat
ial
Trend Analysis. Text Mining Text Data Analysis and Information

Retrieval, Dimensionality
Reduction for Text, Text Mining Approaches.

Web Mining: Web mining introduction, Web
Content Mining, Web Structure Mining, Web

Usage mining, Automatic Classificati
on of web
Documents.

Data Mining for Business Intelligence Applications: Data mining for business

Applications like Balanced Scorecard, Fraud Detection, Market

Segmentation, retail industry,
telecommunications industry, banking & finance and CRM etc.

7


T
otal

35

Reference Books
:

1.

Han, Kamber, "Data Mining Concepts and Techniques", Morgan Kaufmann 2nd Edition

2.

P. N. Tan, M. Steinbach, Vipin Kumar, “Introduction to Data Mining”, Pearson Education

3.

MacLennan Jamie, Tang ZhaoHui and Crivat Bogdan, “Data Mining
with Microsoft SQL Server 2008”, Wiley India Edition.

4.

G. Shmueli, N.R. Patel, P.C. Bruce, “Data Mining for Business Intelligence: Concepts, Techniques, and Applications in Microso
ft Office Excel

with XLMiner”, Wiley India.

5.

Michael Berry and Gordon Lin
off “Data Mining Techniques”, 2nd Edition Wiley Publications.

6.

Alex Berson and Smith, “Data Mining and Data Warehousing and OLAP”, McGraw Hill


C
P

6
2
7



MACHINE LEARNING





C(L,T,P) = 3 (3,0,0)

Units

Contents

Hours


1

Review Basic Tasks, Machine Learning
Overview, Concept Learning, Version Space Learning,
Learning Theory, Decision Tree Learning, Neural Network Learning.

7


2

Methods and underlying problems of Machine Learning, Learning methods such as role, analogical,
EBG, EBL, Chunking.

7


3

Evaluating

hypotheses, Bayesian learning, Minimum Description Length, Naïve Bayes, Custering
Reinforcement Learning

8


4

Learning by examples
-

Version space algorithm and ID3 algorithm. Utilizing ensembles of
classifiers, Bagging and boosting, Instance based learn
ing, RIPPER, Rule Learning

6


5

PCA, Multi dimensional scaling.Important systems and applications to the problem of knowledge
acquisition for expert system.

7


Total

35

Reference Books:

1. Michalsky, T. Mitchell, J.Corbonell, Machine Learning Springer
-
V
erlag.

2. T. M. Mitchell. Machine Learning, McGraw
-
Hill, 1997.


C
P

6
2
9


KNOWLEDGE ENGINEERING AND EXPERT SYSTEMS
C(L,T,P) = 3 (3,0,0)

Units

Contents

Hours


1

History of expert system research
,

Current research activities. Conventional programs


vs. Expert Systems Advantages and limitations of expert systems

7


2


Architecture of an expert system

Components of expert system

Knowledge base, Inference
mechanism User Interface


8


3

Knowledge Engineering.


Nature


of


expert


knowledge.,


Knowledge

acquisition


and


knowledge


representative


e.g.


rule


based


systems,

Semature nets, frames, Validity nature base , working


memory

6

4

Inference


Engine


and

user


interface,


Techniques


for


inference

mechanism,


forward


chaining


and


ba
ckward


chaining

,


Interface language, terminal interface

7

5

Development of expert systems Problem formulation, Search spaces, Task for expert system,
application to


engineering


analysis


and


design

7


Total

35

Reference Books
:

1.

A guide to exper
t system
-

Waterman D.A.
, PHI

2.

Introduction to expert systems
-

Jackson, P. Willy Publications



C
P

6
3
1


HUMAN COMPUTER INTERACTION


C(L,T,P) = 3 (3,0,0)


Units

Contents

H
ours


1

Introduction: Importance of user Interface


definition, importance of g
ood design. Benefits of good
design. A brief history of Screen design
.

7


2

The graphical user interface


popularity of graphics, the concept of direct manipulation, graphical
system, Characteristics, Web user


Interface popularity, characteristics
-

Pri
nciples of user
interface.

8


3

Design process


Human interaction with computers, importance of human characteristics human
consideration, Human interaction speeds, understanding business junctions.

6


4

Screen Designing:
-

Design goals


Screen planning

and purpose, organizing screen elements,
ordering of screen data and content


screen navigation and flow


Visually pleasing composition


amount of information


focus and emphasis


presentation information simply and meaningfully


information retriev
al on web


statistical graphics


Technological consideration in interface
design.

7


5

Windows


New and Navigation schemes selection of window, selection of devices based and
screen based controls.

7


Total

35

Reference Books
:

1.

The essential guide to
user interface design, Wilbert O Galitz, Wiley DreamTech.

2.

Designing the user interface. 3rd Edition Ben Shneidermann , Pearson Education Asia

3.

Human


Computer Interaction. Alan Dix, Janet Fincay, Gre Goryd, Abowd, Russell

Bealg, Pearson Education

4.

Interacti
on Design Prece, Rogers, Sharps. Wiley Dreamtech

5.

User Interface Design, Soren Lauesen , Pearson Education



C
P

659



MAT LAB



C(L,T,P) =
2

(
0
,0,
3
)


Units

List of Experiments

Hours

1

Matlab Interactive Sessions, Menus a
nd the toolbar, Computing with Matlab, Script files and the Editor
Debugger, Matlab Help System, Programming in Matlab.

6

2

Arrays, Multidimensional Arrays, Element by Element Operations, Polynomial Operations Using Arrays ,
Cell Arrays , Structure Arrays

8

3

Elementary Mathematical Functions , User Defined Functions, Advanced Function Programming , Working
with Data Files

6

4

Program Design and Development , Relational Operators and Logical Variables , Logical Operators and
Functions , Conditional stat
ements , Loops , The Switch Structure , Debugging Mat Lab Programs

6

5

XY
-

plotting functions , Subplots and Overlay plots , Special Plot types , Interactive plotting , Function
Discovery , Regression , 3
-
D plots

6


Total

3
2

Reference Books
:

1.

G. H. Gol
ub and C. F. Van Loan, Matrix Computations, 3
rd
Ed., Johns Hopkins University Press, 1996.

2.

B. N. Datta, Numerical Linear Algebra and Applications, Brooks/Cole, 1994 (out of print)

3.

L. Elden, Matrix Methods in Data Mining and Pattern Recognition, SIAM Pres
s, 2007



SM 601


SEMINAR






C(L,T,P) =
5

(0,0,
3
)




S.No.

List of Experiments

Hours

1

1.

Undertaking a
seminar

on an assigned recent topic of the latest technical field.

2.

Preparation and presentations of review articles/papers for National/International J
ournal,
conferences, and symposiums.


3




DI 602


DISSERTATION






C(L,T,P) = 18 (0,0,18)



S.No.

List of Experiments

Hours

1

Undertaking a project on an assigned recent topic of the latest technical field.

18













HS 501



SOFT SKILLS TRAINI
NIG I



C (L, T, P) =
3

(
3
,0,
0
)



Unit

Course Contents

Hours

I


Spoken English


m䥃frob ⡰E灲onunciatio測 䤽inflectionI 䌽Cla物ty C co畲tesyI qZqoneI
rZrn摥rstanding and feedbac欬 oZoate of s灥ech an搠oe灥atitionI bZbmp桡sisF

Body ian杵a来
qraini


Active iiste湩ng

U

II

Introduction to business terms
,
Economic Times Reading
,
Communication skills

8

III

Johari Window Training
,
Firo
-
B Training
,
Relationship Management

10

IV

Role Plays
,
Conflict Management

7

V

I’m OK U’r OK Training

qime ja湡来m
ent q牡i湩ng

S



Total

39


HS 502


SOFT SKILLS TRAININIG I I



C (L, T, P) =
3

(
3
,0,
0
)




Unit

Course Contents

Hours

I


Making impact making business presentations

6

II

Team Management and Collaborative Work Culture

8

III

Training in Anchoring
and Public Speaking

6

IV

Emotional Intelligence Training

7

V

Business Games
,
Business Etiquettes

10



Total

37



HS

601



SOFT SKILLS TRAININIG III



C (L, T, P) =
3

(
3
,0,
0
)




Unit

Course Contents

Hours

I


Group Discussion Training


6

II

Interview Training

8

III

Public Relations Management
,
Press Relations Management

10

IV

Conference and Seminar Management
,
Event management

7

V

Persuasion and Negotiation Skills

6



Total

37