0% found this document useful (0 votes)
34 views52 pages

3 B.tech - Cse Aiml 7 8 Sem

Uploaded by

Saksham Sharma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
34 views52 pages

3 B.tech - Cse Aiml 7 8 Sem

Uploaded by

Saksham Sharma
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 52

B.

Tech Computer Science and Engineering (Artificial Intelligence and Machine Learning)
Modified Scheme of Studies/Examination (w.e.f. Session 2023-24)
Semester VII
S. Course Subject L:T:P Hours/ Credits Examination Schedule Duration
No. No. Week of Exam
(Hrs.)
Major Minor Practical Total
Test Test
1 PC- CS- Data Science with R 3:0:0 3 3 75 25 0 100 3
AIML- Programming
401A
2 HSS- Universal Human 3:0:0 3 3 75 25 0 100 3
403A Values II:
Understanding
Harmony
3 OE OE Elective*-II 3:0:0 3 3 75 25 0 100 3

4 PE Elective* - I 3:0:0 3 3 75 25 0 100 3


5 PE Elective* - II 3:0:0 3 3 75 25 0 100 3
6 PE-LA Elective* – II Lab 0:0:2 2 1 0 40 60 100 3
7 PC- CS- R Programming Lab 0:0:2 2 1 0 40 60 100 3
AIML-
407LA
8 PC- CS- Project** - 1 0:0:10 10 5 0 40 60 100 3
AIML-
409LA
9 PC- CS- Industrial Training*** 0:0:0 0 3 0 100 0 100 3
AIML-
413LA
Total 29 25 300 320 180 800

Code PE Elective*-I Code PE Elective* -II


PE- CS- AIML- 415A Advance Computer PE- CS- AIML- 421A Big Data Analytics for Internet
Architecture of Things
PE- CS- AIML- 417A Soft Computing PE- CS- AIML- 423A Deep Learning
PE- CS- AIML- 419A Data Mining & PE- CS- AIML- 425A Working with Raspberry pi &
Predictive Modelling Arduino platform

Code PE-LA Elective* –II Code OE Elective*-II


PE- CS- AIML- Big Data Analytics for OE-CS- AIML-401 Robotics and Intelligent Systems
421LA Internet of Things Lab
PE- CS- AIML- Deep Learning Lab OE-CS- AIML-403 Probability for Data Science
423LA
PE- CS- AIML- Working with OE-CS- AIML-405 Cluster Computing
425LA Raspberry pi & OE-CS- AIML-407 Microprocessor
Arduino platform Lab
Note: *The students will choose any two departmental Electives courses and One Open Elective
course out of the given elective list in VII Semester.
**Project should be initiated in the beginning of 7thsemester, and should be completed by the
end of 7thsemester with good Report and power-point Presentation etc. ***4-6 weeks’ hand on
training completed after 6thSemester Exams
PC-CS- Data Science with R Programming
AIML-
401A
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
3 0 0 3 75 25 100 3 Hrs.
Purpose To Describe what Data Science is and the skill sets needed to be a data scientist..
Course Outcomes (CO)
CO1 To understand Basics of Data Science statistics, Identify probability distributions.
CO2 To perform basics statistical analysis Using R.
CO3 To Apply basic tools to carry out Exploratory data analysis.
CO4 To explore the components data science Process to interact via machine learning
models.

UNIT -I
Introduction to Data Science - Data Science, History of Data Science, Data Science Process,
Benefits and Uses of data science and big data, how does Data Science relate to other fields,
data science tools, Data analysis and its types.

Data Preprocessing – Introduction, Data types and forms, Various data preprocessing
operations -Data cleaning, data integration, data transformation, data reduction, data
discretization.

UNIT -II

Data plotting and visualization – Introduction, Data visualization software, Data visualization
libraries, Types of data visualization, Basic and specialized data visualization tools.

Statistical Data analysis and probability: Role of statistics and probability in data science,
Descriptive statistics – Measures of frequency, central tendency, dispersion, position,
Dependence and Independence, Conditional Probability, Bayesian probability, Random
Variables, probability distribution

UNIT -III

Introduction to R Programming: What is R, Uses, Advantages and disadvantages, Basics in


R- Syntax, Comments in R, reserved words, identifiers, constants, variables, operators and its
precedence, Strings -Reading strings.

Data types and operations in R: Basic Data types, Vectors, Lists, Matrices, Arrays, Factors,
Data Frames, Data type conversion

UNIT -IV

Connecting R to external Interfaces: CSV Files: Getting and Setting working Directory,
creating, reading, analyzing, writing, Microsoft Excel: Install xlsx package, verifying and
loading, creating, reading, writing.

Machine Learning for Data Science: Regression Methods-Linear, polynomial and logistic,
classification methods, clustering methods, Hidden Markov Model
Data Science Case studies – Data science in Healthcare, Data Science in Ecommerce, Data
Science in Entertainment Industry (preferably on Tableau)

Reference Books:
1. R for Data Analysis in Easy Steps by Mike Mc Grath .
2. Beginning Data Science in R: Data Analysis, Visualization, and Modelling for the
Data Scientist by Thomas Mailund.
3. The Elements of Statistical Learning, 2nd edition. — Springer, 2009. Hastie, T.,
Tibshirani, R., Friedman, J.
4. Statistical Analysis with R for Dummies by: Joseph Schmuller.
5. Machine Learning: A Probabilistic Perspective. Murphy, K. - MIT Press, 2012.
6. “Practical Data Science with R”. Nina Zume l, John Mount. Manning, 2014.
7. Advanced R: Data Programming and the Cloud by by: Matt Wiley,Joshua F. Wiley.
8. Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython ,2nd
edition, Wes McKinney,O’Reilly Media (2017)
HSS- Universal Human Values II: Understanding
403A Harmony
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
3 0 0 3.0 75 25 100 3 Hours
Purpose Purpose and motivation for the course, recapitulation from Universal Human Values-I
Course Outcomes (CO)
CO 1 Development of a holistic perspective based on self-exploration about
CO 2 themselves (human
Understanding being), family,
(or developing society
clarity) andharmony
of the nature/existence.
in the human being,
CO 3 family, society and
Strengthening nature/existence.
of self-reflection.
CO 4 Development of commitment and courage to act.

Module 1: Course Introduction - Need, Basic Guidelines, Content and Process for
ValueEducation
1. Purpose and motivation for the course, recapitulation from Universal Human Values-I
2. Self-Exploration– what is it? - Its content and process; ‘Natural
Acceptance’ and Experiential Validation- as the process for self-exploration
3. Continuous Happiness and Prosperity- A look at basic Human Aspirations
4. Right understanding, Relationship and Physical Facility- the basic requirements for
fulfilment ofaspirations of every human being with their correct priority
5. Understanding Happiness and Prosperity correctly- A critical appraisal of the current
scenario
6. Method to fulfil the above human aspirations: understanding and living in harmony at
various levels.
Include practice sessions to discuss natural acceptance in human being as the innate
acceptance for living with responsibility (living in relationship, harmony and co-existence)
rather than as arbitrariness in choice based on liking-disliking

Module 2: Understanding Harmony in the Human Being - Harmony in Myself!


1. Understanding human being as a co-existence of the sentient ‘I’ and the material ‘Body’
2. Understanding the needs of Self (‘I’) and ‘Body’ - happiness and physical facility
3. Understanding the Body as an instrument of ‘I’ (I being the doer, seer and enjoyer)
4. Understanding the characteristics and activities of ‘I’ and harmony in ‘I’
5. Understanding the harmony of I with the Body: Sanyam and Health; correct appraisal of
Physical needs, meaning of Prosperity in detail
6. Programs to ensure Sanyam and Health.
Include practice sessions to discuss the role others have played in making material goods
available to me. Identifying from one’s own life. Differentiate between prosperity and
accumulation. Discuss program for ensuring health vs dealing with disease

Module 3: Understanding Harmony in the Family and Society- Harmony in


Human-HumanRelationship
1. Understanding values in human-human relationship; meaning of Justice (nine universal
values in relationships) and program for its fulfilment to ensure mutual happiness; Trust
and Respect as the foundational values of relationship
2. Understanding the meaning of Trust; Difference between intention and competence
3. Understanding the meaning of Respect, Difference between respect and differentiation; the
other salient values in relationship
4. Understanding the harmony in the society (society being an extension of family):
Resolution, Prosperity, fearlessness (trust) and co-existence as comprehensive Human
Goals
5. Visualizing a universal harmonious order in society- Undivided Society, Universal Order-
fromfamily to world family.
Include practice sessions to reflect on relationships in family, hostel and institute as
extended family, real life examples, teacher-student relationship, goal of education etc.
Gratitude as a universal value in relationships. Discuss with scenarios. Elicit examples
from students’ lives

Module 4: Understanding Harmony in the Nature and Existence - Whole existence as


Coexistence
1. Understanding the harmony in the Nature
2. Interconnectedness and mutual fulfilment among the four orders of nature- recyclability
and self-regulation in nature
3. Understanding Existence as Co-existence of mutually interacting units in all-pervasive
space
4. Holistic perception of harmony at all levels of existence.
Include practice sessions to discuss human being as cause of imbalance in nature (film
“Home” canbe used), pollution, depletion of resources and role of technology etc.

Module 5: Implications of the above Holistic Understanding of Harmony on


ProfessionalEthics
1. Natural acceptance of human values
2. Definitiveness of Ethical Human Conduct
3. Basis for Humanistic Education, Humanistic Constitution and Humanistic Universal Order
4. Competence in professional ethics: a. Ability to utilize the professional competence
for augmenting universal human order b. Ability to identify the scope and
characteristics of people- friendly and eco-friendly production systems, c. Ability to
identify and develop appropriate technologies and management patterns for above
production systems.
5. Case studies of typical holistic technologies, management models and production systems
6. Strategy for transition from the present state to Universal Human Order: a. At the level
of individual: as socially and ecologically responsible engineers, technologists and
managers b. At the level of society: as mutually enriching institutions and
organizations
7. Sum up.
Include practice Exercises and Case Studies will be taken up in Practice (tutorial)
Sessions eg. to discuss the conduct as an engineer or scientist etc.
READINGS:
Text Book
1. Human Values and Professional Ethics by R R Gaur, R Sangal, G P Bagaria, Excel
Books, New Delhi, 2010
Reference Books
1. Jeevan Vidya: Ek Parichaya, A Nagaraj, Jeevan Vidya Prakashan, Amarkantak, 1999.
2. Human Values, A.N. Tripathi, New Age Intl. Publishers, New Delhi, 2004.
3. The Story of Stuff (Book).
4. The Story of My Experiments with Truth - by Mohandas Karamchand Gandhi
5. Small is Beautiful - E. F Schumacher.
6. Slow is Beautiful - Cecile Andrews
7. Economy of Permanence - J CKumarappa
8. Bharat Mein Angreji Raj - PanditSunderlal
9. Rediscovering India - by Dharampal
10. Hind Swaraj or Indian Home Rule - by Mohandas K. Gandhi
11. India Wins Freedom - Maulana Abdul Kalam Azad
12. Vivekananda - Romain Rolland (English)
13. Gandhi - Romain Rolland (English)

MODE OF CONDUCT
Lecture hours are to be used for lecture/practice sessions.
Lectures hours are to be used for interactive discussion, placing the proposals about the topics
at handand motivating students to reflect, explore and verify them.
Practice hours are to be used for practice sessions.
While analysing and discussing the topic, the faculty mentor’s role is in pointing to essential
elements to help in sorting them out from the surface elements. In other words, help the
students explore the important or critical elements.
In the discussions, particularly during practice sessions, the mentor encourages the student to
connect with one’s own self and do self-observation, self-reflection and self-exploration.
Scenarios may be used to initiate discussion. The student is encouraged to take up” ordinary”
situations rather than” extra-ordinary” situations. Such observations and their analyses are
shared and discussed with other students and faculty mentor, in a group sitting.
Practice experiments are important for the course. The difference is that the laboratory is
everyday life, and practical are how you behave and work in real life. Depending on the
nature of topics, worksheets, home assignment and/or activity are included. The practice
sessions would also provide support to a student in performing actions commensurate to
his/her beliefs. It is intended that this would lead to development of commitment, namely
behaving and working based onbasic human values.
It is recommended that this content be placed before the student as it is, in the form of a basic
foundation course, without including anything else or excluding any part of this content.
Additional content may be offered in separate, higher courses.
This course is to be taught by faculty from every teaching department, including HSS faculty.
Teacher preparation with a minimum exposure to at least one 8-day FDP on Universal Human
Values is deemed essential.

ASSESSMENT:
This is a compulsory credit course. The assessment is to provide a fair state of
development of the student, so participation in classroom discussions, self-assessment,
peer assessment etc. will be used in evaluation.
Example:
Assessment by
faculty mentor: 5 marks
Self-assessment: 5 marks
Assessment by peers: 5 marks
Socially relevant project/Group Activities/Assignments: 10 marks
Semester End Examination: 75 marks
The overall pass percentage is 40%. In case the student fails, he/she must repeat the course.
OE-CS-
AIML- Robotics and Intelligent Systems
401

Lecture Tutorial Practical Credit Major Minor Test Total Time


Test

3 0 0 3 75 25 100 3hrs.

Purpose To impart understanding of the main abstractions and reasoning for Robotics
and Intelligent Systems

Course Outcomes (CO)

CO1 To Understand the basic terminologies in Robotics to develop intelligent


systems

CO2 To Apply the random search and heuristic search for intelligent systems.

CO3 To Understand the abstractions and reasoning for intelligent systems, Apply
the rule-based methods in intelligent systems

CO4 To Identify the characteristics and architectures of algorithms of multi agent


systems, Identify different application areas of Intelligent Systems

UNIT-I

Introduction to robotics- History, Characteristics; Robot applications- Manufacturing


industry, defense, rehabilitation, medical, Robot mechanisms, type of robots, Basic tasks of a
robot, Advantages & Disadvantages of robot, Challenges in Robotics

UNIT-II

Components of robot: Robot components, power source, controllers, manipulator, actuator


drive and its types, end effector, classifying robots, sensors in robots and its types,
transducers, means for programming (Robot programming and interfaces), Degrees of
freedom(DOF)

UNIT-III

Intelligent Systems: Knowledge acquisition, Computational intelligence, Rule-based systems,


Forward-chaining (a data-driven strategy), Conflict resolution, Backward chaining (a goal-
driven strategy), Sources of uncertainty, Bayesian updating, Uncertainty theory.

UNIT-IV

Possibility theory: fuzzy sets and fuzzy logic, Object-oriented systems, Data abstraction,
Inheritance, Encapsulation, Unified Modeling Language (UML), Dynamic (or late) binding.

Key Application Areas: Expert System, Decision Support Systems, Deep Learning: Speech
and vision, natural Language processing, Information Retrieval, Semantic Web.
SUGGESTED BOOKS:

1. Crina Grosan, Ajith Abraham, “Intelligent Systems: A Modern Approach “, Springer-


Verlag, 2011
2. Bogdan M. Wilamowski, J. David Irwin, “The Industrial Electronics Handbook.
Second Edition: Intelligent Systems”, CRC Press, 2011
3. Abraham-Kandel, Gideon-Langholz, “Hybrid-Architectures for Intelligent Systems”,
CRC-Press, 1992
4. Augmented Human, PAPAGIANNIS, Helen, ist print, SPD.

5. Ian Goodfellow, YoshuaBengio and Aaron Courville, "Deep Learning", MIT Press,
http://www.deeplearningbook.org
OE-CS-AIML-
Probability for Data Science
403
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
3 0 0 3 75 25 100 3 Hour
Purpose To understand the foundations of probability and its relationship to statistics
and data science.
Course Outcomes (CO)
CO1 To Understand the mathematical framework for probability theory

CO2 To Understand various kinds of Random Variables that are fundamental to


probabilistic modeling.
CO3 To Learn statistical concepts that are fundamental to conducting statistical
tests on data and understanding whether the data you are analyzing is likely
occurring due to an experimental method or to chance.
CO4 To Explore some introductory concepts from statistics that are helpful in
analyzing data and machine learning.
Unit I

First Tools for looking at data: Datasets, Plotting Data (Bar Charts, Histograms),
Summarizing 1D data – (Mean, standard deviation, Variance, median, interquartile range),
Plotting 2D data – (categorical data, counts and charts, series, scatter plots for spatial data),
Correlation.

Unit II

Basic Ideas in probability –Experiments, outcomes and probability, events, independence,


conditional probability Random variables and expectations- Random variables, expectations
and expected values. Useful probability distributions – Discrete distributions, continuous
distributions, normal distribution, approximating binomials with large N

Unit III

Samples and populations – The sample mean, confidence intervals, significance of evidence –
Significance, evaluating significance, p values, comparing mean of two populations, F tests
and standard deviations, Chi square tests of model fit Extracting important relationships in
high dimensions – Summaries and simple plots (Mean, stem plots and scatterplot matrices),
Using mean and covariance to understand high dimensional data, principal component
analysis, multidimensional scaling

Unit IV

Regression- regression to make predictions, regression to spot trends, linear regression and
least Squares-Linear regression, choosing B, solving least squares problems, residuals, R-
squared, producing good linear regressions Markov chains and hidden Markov models

Textbooks:
1. Sheldon Ross, Introduction to Probability and Statistics for Engineers, 5/e (2014), Elsevier
Reference Books:
1. Morris H. DeGroot and Mark J. Schervish, Probability and Statistics (4/e)(2012), Addison-
Wesley.
2. Blitzstein and Hwang, Introduction to Probability (2015), CRC Press.
3. William Feller, An Introduction to Probability, (3/e) (2008), Volume 1, Wiley.
OE-CS-AIML- Cluster Computing
405

Lecture Tutorial Practical Credit Major Test Minor Test Total Time

3 0 0 3 75 25 100 3 Hrs.

Purpose The objective is to learn emerging techniques in Cluster Computing and its
applications.

Course Outcomes(CO)

CO1 To Remember and understand the basic concepts/Principles of distributed Systems

CO2 To Analyze the Various Concepts of Cluster Computing

CO3 To Able to describe different parallel processing platforms involved in


achieving high performance computing

CO4 To Develop efficient and high performance parallel programming.

UNIT I

Basic concepts in Distributed Systems: Notion of time Distributed Mutual exclusion,


Consensus, Failure models Paradigms for process interaction in distributed programs,
Programming Paradigms, shared memory, Message passing, Workflows

UNIT II
Introduction to Cluster Computing, Cluster Middleware, Early Cluster Architecture and High
Throughput Computing Clusters, Networking, Protocols and I/O for Clusters, Setting Up and
Administering Cluster, Overview of Cluster Computing, Cluster Computer and its
Architecture, Clusters Classifications, Components for Clusters, Cluster Middleware and
Single System Image.

UNIT III
Cluster Technology for High Availability, Performance Models and Simulation, Process
Scheduling, Resource Management and Scheduling, Programming, Environments and Tools,
Load Sharing and Load Balancing, Distributed Shared Memory, Cluster Applications, Cluster
Systems.

UNIT IV
Beowulf Cluster: The Beowulf Model, Application Domains, Beowulf System Architecture,
Software Practices, Parallel Programming with MPL, Parallel Virtual Machine(PVM).
System Infrastructure, Traditional paradigms for distributed computing, Web Services, Grid
standards: OGSA and WSRF, Case Studies of Cluster Systems: COMPaS, NanOS and
PARAM

REFERENCES:
1. Rajkumar Buyya High Performance Cluster Computing: Architectures and
Systems. Prentice-Hall India, 1999.
2. High Performance Cluster Computing: Architectures and Systems, Vol.1,
Prentice Hall
3. Grid and Cluster Computing, Prabhu C.S.R, PHIL earning Private Limited
4. In search of clusters(2nded.), Gregory F.Pfister, IBM, Austin, TX, Prentice-
Hall
5. Distributed and Cloud Computing, First Edition, Geoffrey C.Fox, KaiHwang,
Jack J.Dongarra, Elsevier India Pvt. Ltd.-New Delhi
6. Laurence T.Yang, Minyi Guo – High Performance Computing Paradigm and
Infrastructure JohnWiley
OE-CS- Microprocessor
AIML-407
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
3 0 0 3 75 25 100 3Hour
Purpose To learn the architecture and programming of Intel family microprocessors and its
interfacing.
Course Outcomes(CO)
CO1 To study the Architecture of 8086 microprocessors
CO2 To implement the interfacing of memories to 8086 Microprocessor
C O3 To learn and analyze the instruction set of 8086 Microprocessor and implementation of
assembly language programming of 8086 Microprocessor.
CO4 To design and implement the interfacing of interrupts, basic I/O and DMA with 8086
Microprocessor

UNIT-I

8086 CPU ARCHITECTURE: 8086 Block diagram; description of data registers, address
registers; pointer and index registers, PSW, Queue, BIU and EU. 8086 Pin diagram
descriptions. Generating 8086 CLK and reset signals using 8284. WAIT state generation.
Microprocessor BUS types and buffering techniques, 8086 minimum mode and maximum
mode CPU module.
UNIT-II
Main Memory System Design: Memory devices, 8086 CPU Read/Write timing diagrams in
minimum mode and maximum mode. Address decoding techniques. Interfacing SRAMS;
ROMS/PROMS. Interfacing and refreshing DRAMS.

UNIT-III
8086 Instruction Set: Instruction formats, addressing modes, Data transfer instructions, string
instructions, logical instructions, arithmetic instructions, transfer of control instructions;
process control instructions; Assembler directives.
8086 Programming Techniques: Writing assembly Language programs for logical processing,
arithmetic processing, timing delays; loops, data conversions.

UNIT-IV
Basic I/O Interface: Parallel and Serial I/O Port design and address decoding. Memory
mapped I/O Vs Isolated I/O Intel’s 8255 and 8251- description and interfacing with 8086.
ADCs and DACs, - types, operation and interfacing with 8086. Interfacing Keyboards,
alphanumeric displays, multiplexed displays, and stepper motor, optical encoder with 8086.
Interrupts and DMA: 8086 Interrupt mechanism; interrupt types and interrupt vector table.
Applications of interrupts, Intel’s 8259. DMA operation. Intel’s 8237.

Suggested Books:
1. BarryB.Brey, “TheIntelMicroprocessor8086/8088,80186”, PearsonEducation,
EighthEdition,2009 1st and 4th Edition
2. D.V. Hall, Microprocessors and Interfacing, McGrawHill2nded.
3. Liu, Gibson, “Microcomputer Systems: The8086/88Family”, 2ndEdition, PHI,2005
4. Kenneth Ayala, “The8086Microprocessor: Programming & Interfacing the PC”,
Cengage Learning,
5. Indian Edition, 2008
6. Kip Irvine,” Assembly language for IBM PC”, PHI,2ndEdition,1993, 40% 3rd
Edition
7. Peter Abel,” Assembly language programming”, PearsonEdu,5thEdition,2002
8. Uffen back, “The8086FamilyDesign” PHI 1st and 2ndEdition.
9. Walter A Triebel and Avtar Singh; The8088 and8086Microprocessors 4th Edition
PE-CS-AIML-
Advance Computer Architecture
415A
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
3 0 0 3 75 25 100 3 Hour
Purpose To enable students to learn various computational models, design paradigms
of advanced computer architecture, parallelism approaches and techniques
for static and dynamic interconnections.
Course Outcomes (CO)
CO1 To Classify and interpret various paradigms, models and micro-architectural
design of advanced computer architecture as well as identify the parallel
processing types and levels for achieving optimum scheduling
CO2 To Identify the roles of VLIW & superscalar processors and branch
handling techniques for performance improvement
CO3 To Analyze and interpret the basic usage of various MIMD architectures and
relative importance of various types of static and dynamic connection
networks for realizing efficient networks.
CO4 To Examine the various types of processors and memory hierarchy levels
and cache coherence problem including software and hardware based
protocols to achieve better speed and uniformity.

Unit-I

Parallel Computer Models – Introduction to parallel computing, Need for parallel computing,
Constraints of conventional architecture, Evolution of parallel processors -Basic
terminologies, Features, evolution and future trends, Parallelism in uniprocessor system -
Uniprocessor architecture and mechanism, Multiprocessors and multicomputer -UMA,
NUMA, COMA and NORMA models, Multivector and SIMD computers

Unit-II

Parallel Architectural Classification Schemes – Flynn, Feng, Handler classification,


classification based on coupling between Processing elements, based on grain size, based on
modes of access memory; Instruction level parallelism and thread level parallelism.

Program and Network properties: Introduction, Conditions of parallelism, Types of


dependencies, hardware and software parallelism, Program partitioning and scheduling,
program flow mechanisms, control flow, data flow, reduction computers

Unit-III

Parallel Algorithms and Programming – Introduction, characteristics of parallel algorithms,


Parallel programming techniques, Models of parallel programming, Classification of parallel
algorithms, Performance of parallel algorithms

Vector processing - Introduction, comparison of vector and array processors, basic vector
architecture and its classification, Terminologies related to vector processing, vector
instruction types, vector performance modeling, vectorization, Design of a vectorizing
compiler
UNIT – IV

Pipelining – Introduction, Pipeline-Principle and implementation (Linear pipeline processor,


Clock period, speed up, efficiency, throughput), Nonlinear pipeline processor, Classification
of pipeline processor – Based on levels of processing, based on pipeline configuration,
General pipelines, Different pipeline design – multiply and divide pipeline design, Instruction
pipeline design, mechanisms for instruction pipelining

Reference Books:
1. D.Sima, T.Fountain, P.Kasuk, Advanced Computer Architecture-A Design Space
Approach, Pearson Education.
2. Kai Hwang and Naresh Jotwani, Advanced Computer Architecture-Parallelism,
Scalability, Programmability, McGraw Hill.
3. M.J. Quinn, Parallel Computing: Theory and Practice, Second Edition, McGraw Hill.
4. J. L. Hennessy and D. A. Patterson, Computer Architecture: A Quantitative approach,
Morgan Kaufmann/Elsevier.
5. T.G. Lewis and H. EI- Rewini, Introduction to parallel computing, Prentice Hall.
6. Nicolas Carter, Computer Architecture, McGraw Hill.
PC-CS-
AIML Soft Computing
-417A
Lecture Tutorial Practical Credit Major Minor Test Total Time
Test
3 0 0 3 75 25 100 3 Hrs.
Purpose Soft Computing is a consortium of methodologies which collectively provide a body of
concepts and techniques for designing intelligent systems.

Course Outcomes(CO)
CO1 The main objective of the Soft Computing Techniques to Improve Data Analysis
CO2 Tostrengthenthedialoguebetweenthestatisticsandsoftcomputingresearchcommunitiesin
order to cross-pollinate both fields
CO3 To develop Solutions and generate mutual improvement activities
CO4 To develop practical data analysis skills, which can be applied to practical problems

Unit-I
Introduction: What is Soft Computing. Difference between Hard and Soft
computing, Requirement of Soft computing, Major Areas of Soft Computing,
Applications of Soft Computing.

Unit-II
Neural Network, Learning rules and various activation functions, Single layer
Perceptron, Back Propagation networks, Architecture of Backpropagation (BP)
Networks, Backpropagation Learning, Introduction to counter propagation,
Adaptive Resonance theory and Self Organizing Map, Recent Applications.

Unit-III
Fuzzy Systems: Fuzzy logic, fuzzy sets - properties - operations on fuzzy sets,
fuzzy relations - operations on fuzzy relations
Fuzzy membership functions, fuzzification, Methods of membership value
assignments – intuition – inference – rank ordering, Lambda – cuts for fuzzy sets,
Defuzzification methods

Unit-IV
Genetic Algorithm: History of Genetic Algorithms(GA), Working Principle, Various
Encoding methods, Fitness function, GA Operators-Reproduction, Crossover, Mutation,
Convergence of GA, Bitwise operation in GA, Multi-level Optimization, Genetic-neuro
hybrid systems, Genetic Fuzzy rule based system

Suggested Books:
1. Principles of Soft Computing by S. N. Sivanandam &S. N. Deepa byWiley, India
edition. 1st and 2ndEdition
2. Neural Networks, Fuzzy Logic and Genetic Algorithms: Synthesis &
Applications, S.Rajasekaran,G. A. Vijayalakshami, PHI. 2nd and 4th Edition
3. Genetic Algorithms: Search and Optimization, E.Goldberg.
4. Neuro-FuzzySystems,ChinTengLin,C.S.GeorgeLee,PHI.
5. Build_Neural_Network_With_MS_Excel_sample by Joechoong.
PE-CS- Data Mining and Predictive Modelling
AIML-419A
L T P Credit Major Test Minor Test Total Time
3 0 0 3 75 25 100 3 Hour
Purpose The course provides grounding in basic and advanced methods to learn, how to
develop models to predict categorical and continuous outcomes, using such
techniques as neural networks, decision trees, logistic regression, support vector
machines and Bayesian network models. To know the use of the binary classifier
and numeric predictor nodes to automate model selection. To advice on when and
how to use each model. Also learn how to combine two or more models to improve
prediction.

Course Outcomes (CO)


CO1 To learn, how to develop models to predict categorical and continuous outcomes,
using such techniques as neural networks, decision trees, logistic regression, support
vector machines and Bayesian network models.

CO2 To know the use of the binary classifier and numeric predictor nodes to automate
model selection.

CO3 To advice on when and how to use each model. Also learn how to combine two or
more models to improve prediction.

CO4 To Apply predictive modeling approaches using a suitable package such as SPSS
Modeler

Unit 1

Introduction to Data Mining Introduction, what is Data Mining, Concepts of Data mining,
Technologies Used, Data Mining Process, KDD Process Model, CRISP – DM, Mining on
various kinds of data, Applications of Data Mining, Challenges of Data Mining.

Unit 2

Data Understanding and Preparation Introduction, Reading data from various sources, Data
visualization,Distributions and summary statistics, Relationships among variables, Extent of
Missing Data. Segmentation, Outlier detection, Automated Data Preparation, combining data
files, Aggregate Data, Duplicate Removal, Sampling DATA, Data Caching, Partitioning data,
Missing Values.

Unit 3

Model development & techniques Data Partitioning, Model selection, Model


Development Techniques, Neural networks, Decision trees, Logistic regression, Discriminant
analysis, Support vector machine, Bayesian Networks, Linear Regression, Cox Regression,
Association rules.

Unit 4:

Model Evaluation and Deployment Introduction, Model Validation, Rule Induction Using
CHAID, Automating Models for Categorical and Continuous targets, Comparing and
Combining Models,Evaluation Charts for Model Comparison, MetaLevel Modeling,
Deploying Model, Assessing ModelPerformance, Updating a Model.

Reference Books:

1. Predictive & Advanced Analytics (IBM ICE Publication)

2. Data Mining: Concepts and Techniques by Jiawei Han

3. Data Mining: Practical Machine Learning Tools and Techniques by Mark A.


Hall, Ian H. Witten
PE-CS- Big Data Analytics for Internet of Things
AIML-421A
L T P Credit Major Test Minor Test Total Time
3 0 0 3 75 25 100 3 Hour
Purpose The course provides grounding in basic and advanced methods to big data
technology and tools.
Course Outcomes (CO)
CO1 To Understand Big Data and its analytics in the real world.
CO2 To Analyze the Big Data framework like Hadoop and NOSQL to efficiently store
and process Big Data to generate analytics.
CO3 To Design of Algorithms to solve Data Intensive Problems using MapReduce
Paradigm
CO4 To Design and Implementation of Big Data Analytics using pig and spark to solve
data intensive problems and to generate analytics.

UNIT I

Introduction: Big data Concepts, Needs and Challenges of big data. Types and source
of big data. Component of system data, access, storage. Data intelligence, Data integration.

UNIT II

Distributed file system, Big Data and its importance, Four Vs, Driversfor Big
data, big data analytics, big data applications. Algorithms using map reduce,
Matrix-VectorMultiplicationby Map Reduce.

UNIT III

Introduction to Hadoop- Big Data – Apache Hadoop & Hadoop EcoSystem –


Moving Data in and out of Hadoop– Understanding inputs and outputs of Map
Reduce-Data Serialization.

UNIT IV

Hadoop Architecture - Hadoop Architecture, Hadoop Storage: HDFS, Common


Hadoop Shell commands, Anatomy of File Write and Read. Name Node,
Secondary Name Node, and Data Node, Hadoop Map Reduce.

Reference Books:

1. Borislublinsky,Kevint.Smith,AlexeyYakubovich,
“ProfessionalHadoopSolutions”, Wiley, ISBN:9788126551071,2015.
2. ChrisEaton,Dirkderoos, etal.,“UnderstandingBigdata”,McGrawHill,2012.
3. TomWhite, “HADOOP: ThedefinitiveGuide”, OReilly2012.
4. VigneshPrajapati, “BigDataAnalyticswithRandHadoop”, PacketPublishing2013.
PE-CS-AIML- Deep Learning
423A
L T P Credit Major Minor Total Time
Test Test
3 0 0 3 75 25 100 3 Hour
Purpose The course provides grounding in basic and advanced methods to
understand the theoretical foundations, algorithms and methodologies of
Neural Network. To design and develop an application using specific
deep learning models. To provide the practical knowledge in handling and
analysing real world applications.

Course Outcomes (CO)


CO1 To Recognize the characteristics of deep learning models that are useful
to solve real-world problems.

CO2 To Understand different methodologies to create application using deep


nets.
CO3 To Identify and apply appropriate deep learning algorithms for analyzing
the data for variety of problems.

CO4 To Implement different deep learning algorithms. Design the test


procedures to assess the efficacy of the developed model. Combine
several models in to gain better results

Unit:1

Basics of Machine Learning algorithms, Maximum likelihood estimation, Building machine


learning algorithm, Neural Networks Multilayer Perceptron, Back-propagation algorithm and
its variants Stochastic gradient decent, Curse of Dimensionality

Unit 2

Deep Learning Architectures, Representation Learning, Width and Depth of Neural


Networks, Activation Functions: RELU, LRELU, ERELU, Unsupervised Training of Neural
Networks, Restricted Boltzmann Machines, Auto Encoders, Deep Learning Applications

Unit 3

Convolutional Neural Networks, Architectural Overview, Motivation, Layers, Filters,


Parameter sharing, Regularization, Popular CNN Architectures: ResNet, AlexNet -
Applications

Unit 4

Transfer Learning Techniques, Variants of CNN: DenseNet, PixelNet, Recurrent Neural


Networks, Bidirectional RNNs, Encoder-decoder sequence to sequence architectures - BPTT
for training RNN, Long Short Term Memory Networks.
TEXT BOOKS

1.Ian Goodfellow, YoshuaBengio and Aaron Courville, “Deep Learning”, MIT Press, 2017.
2. Josh Patterson, Adam Gibson "Deep Learning: A Practitioner's
Approach", O'Reilly Media, 2017
3. Umberto Michelucci “Applied Deep Learning. A Case-based Approach to Understanding
DeepNeural Networks” Apress, 2018.

Reference Books
1. Kevin P. Murphy "Machine Learning: A Probabilistic Perspective ", The MIT
Press, 2012.
2. EthemAlpaydin, "Introduction to Machine Learning”, MIT Press, Prentice Hall of
India, Third
Edition 2014.
3.Giancarlo Zaccone, Md. RezaulKarim, Ahmed Menshawy"Deep Learning with
TensorFlow:
PE-CS- Working with Raspberry pi & Arduino platform
AIML-425A
L T P Credit Major Test Minor Test Total Time
3 0 0 3 75 25 100 3 Hour
Purpose The course provides the IOT related infrastructure and various IOT devices. This
course will help you know about the embedded system, IOT architecture. To
understand the various applications and future aspects of IOT world. This course will
help to do various Arduino related projects like intelligent home locking system.
Along with Arduino, in the later on sections, we will study Raspberry pi. Sensors and
actuators related to raspberry pi and various applications and related projects.

Course Outcomes (CO)


CO1 To learn the embedded system and their working and IOT fundamentals.

CO2 To know the use of Arduino and its basic concepts. Also understand the various
Arduino based projects.

CO3 To understand the raspberry Pi and programming done with it.

CO4 To Apply programming and hardware interfaces with Raspberry Pi and various
projects.

Unit I

Introduction to embedded system, Understanding Embedded System, Overview of basic


electronics and digital electronics, Microcontroller vs. Microprocessor, Common features of
Microcontroller, Different types of microcontrollers, Overview of IoT, Understanding IoT
fundamentals, IoT Architecture, protocols, Various Platforms for IoT, Real time Examples of
IoT, Overview of IoT components and IoT Communication Technologies

Unit II

Getting Started with Arduino: Introduction to Arduino, Pin configuration and architecture.,
Device and platform features, Concept of digital and analog ports, Arduino Basic Concepts:
Arduino data types, Variables and constants, Operators, Control Statements, Arrays,
Functions

Arduino Projects: Intelligent home locking system, Intelligent water level management
system, Home automation using RFID, Real time clock-based home automation, Intelligent
Automatic Irrigation System

Unit III

Getting Started with Raspberry Pi: Basic functionalities of Raspberry Pi board and its
processor, Pin Description of Raspberry Pi, Understanding SoC architecture and SoCs used in
Raspberry Pi

Programming the Raspberry Pi: Python: Introduction to Python Programming language,


Python vs Other Languages, Python Programming Environment, Variables, Keywords, Data
Types in Python, Loops, Conditional Statement, Function, Function Argument, Flow Control,
Numpy, Importing Libraries, PIP (Python Installation Package) and Customized libraries,
Application of Pythons

Unit IV

Interfacing of Sensors and Actuators with RPi:Temperature and Humidity Sensor (DHT11),
Motion Sensor (PIR), Obstacle detection using Ultrasonic sensor, etc.Robotics Motion
Raspberry Pi: DC, Servo, Stepper Motor, Camera Interfacing

References Books:

1. Arduino Cookbook by Michael Margolis, O'Reilly Media, Inc., 1st edition.

2. Arduino for beginners: Essential Skills Every Maker Needs, John Baichtal, Person
Education, Inc., 1st edition

3.Raspberry Pi 3 An Introduction to Using with PythonScratch, Javascript and more,


Gary Mitnick, CreateSpace Independent Publishing Platform, 2017.

4.Raspberry Pi for Python Programmers Cookbook, Tim Cox, Packt Publishing Limited;
2nd Revised edition, 2016.

5.Raspberry Pi User Guide, Eben Upton and Gareth Halfacreee, John Wiley & Sons,
2016.

6. Internet of Things – A hands-on approach, Arshdeep Bahga, Vijay Madisetti,


Universities Press, 2015

7. Raj Kamal, “Internet of Things: Architecture and Design Principles”, 1st Edition,
McGraw Hill Education,2017.
PE-CS- Big Data Analytics for Internet of Things Lab
AIML-
421LA
Lecture Tutorial Practical Credit Minor Practical Total Time
Test
0 0 2 1 40 60 100 3 Hrs.
Purpose To Describe what Data Science is and the skill sets needed to be a data scientist..
Course Outcomes (CO)
CO1 Install and use R for simple programming tasks. Extend the functionality of R by using
add-on packages.

CO2 To perform basics statistical analysis Using R.


CO3 To Apply basic tools to carry out Exploratory data analysis.
CO4 To explore the components data science Process to interact via machine learning
models.

LIST OF PRACTICALS

1. Installation of Single Node Hadoop Cluster on Ubuntu

2. Hadoop Programming: Word Count Map Reduce Program Using Eclipse

3. Implementing Matrix Multiplication Using One Map-Reduce Step.

4. Implementing Relational Algorithm on Pig.

5. Implementing database operations on Hive.

6. Implementing Bloom Filter using Map-Reduce

7. Implementing Frequent Item set algorithm using Map-Reduce.

8. Implementing Clustering algorithm using Map-Reduce

9. Implementing Page Rank algorithm using Map-Reduce

10. Mini Project:

Few topics for Projects:

a. Twitter data analysis

b. Fraud Detection

c. Text Mining

d. Equity Analysis etc.


PC-CS- Deep learning Lab
AIML-
423LA
Lecture Tutorial Practical Credit Minor Practical Total Time
Test
0 0 2 1 40 60 100 3 Hrs.
Purpose To Describe what Data Science is and the skill sets needed to be a data scientist..
Course Outcomes (CO)
CO1 To understand the deep learning.

CO2 To perform basics deep learning networks


CO3 To apply various deep learning networks in real world life..
CO4 To implement deep learning modules.

LIST OF PRACTICALS

1. Write a program to implement different activation functions to train Neural Network.

2. Write a program to implement different Learning Rules.

3. Write a program to implement Perceptron Networks.

4. Write a program to implement Adaline network for system identification.

5. Write a program to implement Madaline network

6. Write a program to implement Pattern matching using different rules.

7. Create a project that focuses on how machine learning is used in healthcare.

8. Project related to application of machine learning in business analysis.

9. Project related to application of machine learning in sports analytics.

10. Project related to application of machine learning in Time Series Analysis &
Forecasting.
PE-CS- Working with Raspberry pi & Arduino platform Lab
AIML-
425LA
Lecture Tutorial Practical Credit Minor Practical Total Time
Test
0 0 2 1 40 60 100 3 Hrs.
Purpose To describe what Data Science is and the skill sets needed to be a data scientist.
Course Outcomes (CO)
CO1 To understand the Raspberry Pi.

CO2 To perform basics practicals using Arduino platform


CO3 To apply various Raspberry pi & Arduino platform in real world life..
CO4 To implement and connect with MySQL database

LIST OF PRACTICALS

1. Study and installation of Raspberry- pi

2. To write a program to sense the available networks using Arduino

3. To write a program to measure the distance using ultrasonic sensor and make LED
blink using Arduino.

4. To write a program to detects the vibration of an object with sensor using Arduino.

5. To write a program to connect with the available Wi-Fi using Arduino

6. To write a program to sense a finger when it is placed on the board Arduino.

7. To write a program to get temperature notification using Arduino.

8. To write a program for LDR to vary the light intensity of LED using Arduino.

9. To write a program to install MySQL database in Raspberry pi.

10. To write a program to work with basic MySQL queries by fetching data from
database in Raspberry pi.

11. To write a program to switch light on when the input is 1 and switch the light off
when the input is 0 using Raspberry

Raspberry Pi Projects: Set up a Pi motion detector, set up Pi ADC/DAC, construct a digital


weather station, construct a traffic light controller.
PC-CS- R Programming lab
AIML-
407LA
Lecture Tutoria Practical Credi Minor Practical Total Time
l t Test
0 0 2 1 40 60 100 3 Hrs.
Purpose To Describe what Data Science is and the skill sets needed to be a data scientist..
Course Outcomes (CO)
CO1 Install and use R for simple programming tasks. Extend the functionality of R by using
add-on packages.

CO2 To perform basics statistical analysis Using R.


CO3 To Apply basic tools to carry out Exploratory data analysis.
CO4 To explore the components data science Process to interact via machine learning
models.

LIST OF PRACTICALS

1. Write an R script, to create R objects for calculator application and save in a specified
location in disk.

2. Write an R script to find basic descriptive statistics using summary, str, quartile function
on sample datasets.

3. Write an R script to find subset of dataset by using subset (), aggregate () functions on
sample dataset.

4. Write an R script for Reading different types of data sets (.txt, .csv) from web and disk and
writing in file in

specific disk location.

5. Write an R script for Reading Excel data sheet and XML dataset.

6. Find the data distributions using box and scatter plot of sample dataset.

a. Find the outliers using plot.

b. Plot the histogram, bar chart and pie chart on same data.

7. How to find a correlation matrix and plot the correlation on sample data set.

a. Plot the correlation plot on dataset and visualize giving an overview of relationships among
data

b. Analysis of covariance: variance (ANOVA), if data have categorical variables

8. Import a data from web storage. Name the dataset and now do Logistic Regression to find
out relation between variables that are affecting the admission of a student in a institute based
on his or her GRE score, GPA obtained and rank of the student. Also check the model is fit or
not. require (foreign), require(MASS).

9. Apply multiple regressions, if data have a continuous independent variable. Apply on


above dataset (in Que

10. Apply regression Model techniques to predict the data on above dataset (in Que 8).
S. Course Subject L:T:P Hours/ Credits Examination Schedule Duration
No. No. Week of Exam
(Hrs.)
Major Minor Practical Total
Test Test
1 PC- Project**- 0:0:10 10 5 0 40 60 100 3 hours
CS- I
AIML-
409LA

S. No. Course Subject L:T: Hou Credi Examination Schedule Durati


No. P rs/ ts on of
Wee Exam
k (Hrs.)
Maj Min Practic Total
or or al
Test Test
1 PC-CS- Industrial 0 0 3 0 100 0 100 3 hours
AIML- Training***
413LA
B. Tech Computer Science and Engineering (Artificial Intelligence and Machine Learning)
Modified Scheme of Studies/Examination (w.e.f. Session 2023-24)
Semester VIII
S. No. Course No. Subject L:T:P Hours/ Credits Examination Schedule Duration
Week of Exam
(Hrs.)
Major Minor Practical Total
Test Test
1 PC- CS- AIML- Optimization 3:0:0 3 3 75 25 0 100 3
402A Method in ML
2 HSS-404A Entrepreneurship 3:0:0 3 3 75 25 0 100 3
and Start-ups
2 OE OE Elective*-III 3:0:0 3 3 75 25 0 100 3

3 PE Elective* – III 2:0:0 2 2 75 25 0 100 3


4 PE Elective* - IV 2:0:0 2 2 75 25 0 100 3
5 PC- CS- AIML- Optimization Lab 0:0:2 2 1 0 40 60 100 3
406LA
6 PC- CS- AIML- Advance AI 0:0:2 2 1 0 40 60 100 3
408LA Application Lab
7 PC- CS- AIML- Project**-II 0:0:10 10 5 0 100 100 200 3
410LA
8 HM- CS- AIML- General Fitness & 0:0:0 0 0 0 0 100 100 3
412A Proficiency
Total 27 20 300 280 320 900

Code PE-Elective* III Code PE-Elective* IV


PE- CS- Reinforcement Learning PE- CS- AIML- 422A Augmented Reality
AIML- 402A
PE- CS- Social Networks PE- CS- AIML- 424A Advance Machine Learning
AIML- 416A
PE- CS- Neural Network and Fuzzy PE- CS- AIML- 426A Natural Language Processing
AIML- 420A Logic systems

Code OE Elective*-III
OE-CS-AIML-402 Cyber Law and Ethics
OE-CS-AIML-404 Cryptographic Fundamentals
OE-CS-AIML-406 Network Operating System
OE-CS-AIML-408 Reasoning, Problem Solving and Robotics
OE-CS-AIML-410 Image Processing and Recognition

Note: *The students will choose any two departmental Electives courses and One Open Elective
course out of the given elective list in VIII Semester.
**Project should be initiated in the beginning of 8thsemester, and should be completed by the
end of 8thsemester with good Report and power-point Presentation etc.
PC-CS-AIML-
Optimization Method in ML
402A
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
3 0 0 3 75 25 100 3 Hour
Purpose To equip students with advanced techniques and methods in optimization
that are tailored to large-scale statistics and machine learning problems
Course Outcomes (CO)
CO1 To understand the basics of convex optimization.

CO2 To learn the basics of gradient based methods.


CO3 To apply the operator’s splitting methods.
CO4 To know about stochastic and non-convex optimization dual averaging.

UNIT I

Basics of convex optimization: convex sets, convexity-preserving operations, examples


of convex programs (linear programming (LP), second-order cone programming
(SOCP), semi-definite programming (SDP)), convex relaxation, KKT conditions,
duality

UNIT II

Gradient-based methods: gradient descent, sub-gradient, mirror descent, Frank–Wolfe


method, Nesterov’s accelerated gradient method, ODE interpretations, dual methods,
Nesterov’s smoothing, proximal gradient methods, Moreau–Yosida regularization

UNIT III

Operator splitting methods: Augmented Lagrangian methods, alternating direction


method of multipliers (ADMM), monotone operators, Douglas–Rachford splitting,
primal and dual decomposition

UNIT IV

Stochastic and non-convex optimization dual averaging, Polyak–Juditsky averaging,


stochastic variance reduced gradient (SVRG), Langevin dynamics, escaping saddle
points, landscape of non-convex problems, deep learning

Suggested Books:

1. Optimization in Machine Learning and Applications, Anand J. Kulkarni,


Suresh Chandra Satapathy, 2019

2. Linear Algebra and Optimization for Machine Learning, Charu C. Aggarwal,


2020.
HSS-404A Entrepreneurship and Start-ups
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
3 0 0 3 75 25 100 3 Hour
Purpose To expose students to the joys and skills of being an entrepreneur.

Course Outcomes (CO)


CO1 To understand the basics of Entrepreneurship
CO2 To learn the basics of Creative and Design Thinking
CO3 To apply the Business Enterprises
CO4 To know about business models

Unit I
Introduction to Entrepreneurship, Meaning and concept of entrepreneurship, the history of
entrepreneurship development, role of entrepreneurship in economic development, Myths
about entrepreneurs, types of entrepreneurs.
Unit II
The skills/ traits required to be an entrepreneur, Creative and Design Thinking, the
entrepreneurial decision process, entrepreneurial success stories.
Unit III
Crafting business models and Lean Start-ups: Introduction to business models; Creating value
propositions-conventional industry logic, value innovation logic; customer focused
innovation; building and analysing business models; Business model canvas, Introduction to
lean start-ups, Business Pitching.
Unit IV
Institutions Supporting Small Business Enterprises: Central level institutions. State level
institutions. Other agencies. Industry Associations. Class exercise- discussions on current
government schemes supporting entrepreneurship and finding out which scheme will most
suit the business plan devised by the student.

Text Books:
 Kuratko, D , Hornsby J.S. (2017) New Venture Management: Entrepreneur’s roadmap
 Hisrich, R.D., Manimala, M.J., Peters, M.P., Shepherd, D.A.: Entrepreneurship, Tata
McGraw Hill
 Ries, Eric(2011)The lean Start-up: How constant innovation creates radically
 S. Carter and D. Jones-Evans (2012), Enterprise and small business- Principal Practice and
Policy, Pearson Education (2006)
Reference books:
 Guillebeau, C (2015) The $100 Startup: Fire Your Boss, Do What You Love and Work
Better To Live
 Prasad, Rohit (2013), Start-up sutra: what the angels won’t tell you about business and life,
Hachette India.
 Charantimath, P. (2009). Entrepreneurship Development: Small Business Enterprises. Pearson
OE-CS- Cyber Law and Ethics
AIML-402

Lecture Tutorial Practical Credit Major Minor Total Time


Test Test
3 0 0 3 75 25 100 3 Hours
Purpose The course deals with all the aspects of Cyber law as per Indian/IT act. It also covers
overview of Cyber Ethics, Intellectual Property Right and Trademark Related laws
with respect to Cyber Space.
Course Outcomes (CO)
CO 1 To give overview of Cyber Ethics, Intellectual Property Right and Trademark Related
laws with respect to Cyber Space.
CO 2 To analyze and evaluate existing legal framework and laws on cyber security.
CO 3 To analyze and evaluate the Intellectual rights and copyrights.
CO 4 To understand cyber ethics.

Unit-1: Introduction to Cyber Law


Evolution of computer technology, emergence of cyber space. Cyber Jurisprudence,
Jurisprudence and law, Doctrinal approach, Consensual approach, Real Approach, Cyber
Ethics, Cyber Jurisdiction, Hierarchy of courts, Civil and criminal jurisdictions, Cyberspace-
Web space, Web hosting and web Development agreement, Legal and Technological
Significance of domain Names, Internet as a tool for global access.

Unit-2: Information Technology Act


Overview of IT Act, 2000, Amendments and Limitations of IT Act, Digital Signatures,
Cryptographic Algorithm, Public Cryptography, Private Cryptography, Electronic
Governance, Legal Recognition of Electronic Records, Legal Recognition of Digital
Signature, Certifying Authorities, Cyber Crime and Offences, Network Service Providers
Liability, Cyber Regulations Appellate Tribunal, Penalties and Adjudication.

Unit-3: Cyber Law and Related Legislation


Patent Law, Trademark Law, Copyright, Software – Copyright or Patented, Domain Names
and Copyright disputes, Electronic Data Base and its Protection, IT Act and Civil Procedure
Code, IT Act and Criminal Procedural Code, Relevant Sections of Indian Evidence Act,
Relevant Sections of Bankers Book Evidence Act, Relevant Sections of Indian Penal Code,
Relevant Sections of Reserve Bank of India Act, Law Relating To Employees And Internet,
Alternative Dispute Resolution , Online Dispute Resolution (ODR).

Unit-4: Cyber Ethics


The Importance of Cyber Law, Significance of cyber Ethics, Need for Cyber regulations and
Ethics. Ethics in Information society, Introduction to Artificial Intelligence Ethics: Ethical
Issues in AI and core Principles, Introduction to Block chain Ethics.
Suggested Books:
1. Cyber Security : Understanding Cyber Crimes , Computer Forensics and Legal
Perspectives By Nina Godbole, Sunit Belapur , Wiley
2. Understanding cybercrime: phenomena , and legal challenges response, ITU 2012.
OE-CS- Cryptographic Fundamentals
AIML-
404
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
3 0 0 3 75 25 100 3
Hours
Purpose To Understand various cryptographic algorithm, public-key cryptosystem and
fundamental ideas of public-key cryptography.
Course Outcomes(CO)
CO1 To Student will be able to understand basic cryptographic algorithms.
CO2 To Able to understand the fundamental ideas of public-key cryptography.
CO3 To Analyze and compare symmetric-key encryption public-key encryption
schemes based on different security models
CO4 To Able to understand the PKI infrastructure.

Unit-I
Cryptography Concept: Introduction, plain text and cipher text, substitution techniques,
transposition techniques, encryption and decryption, symmetric and asymmetric key
cryptography, steganography, key range and key size, possible types of attacks Historical
Ciphers, Computational Security, Semantic Security, Pseudorandom Generators (PRGs) PRF,
PRP and SPRP.

Unit-II
Symmetric key Ciphers: Block Cipher principles, Modes of Operations of Block Ciphers,
DES, AES, Stream ciphers.
Cryptographic Hash Functions: MAC, Information-theoretic Secure MAC, Cryptographic
Hash Functions, Birthday Attacks on Cryptographic Hash Functions, Applications of Hash
Functions, Generic Constructions of Authenticated Encryption Schemes.

Unit-III
Asymmetric key Ciphers: Discrete-Logarithm Problem, Computational Diffie-Hellman
Problem, Decisional Diffie-Hellman Problem, Elliptic-Curve Based Cryptography and
Public-Key Encryption, El Gamal Encryption Scheme, RSA Assumption, CCA -secure
Public-key Hybrid Ciphers Based on Diffie-Hellman Problems and RSA-assumption, Digital
Signatures.

Unit-IV
Key Management and Distribution: Symmetric Key Distribution Using Symmetric &
Asymmetric Encryption, Distribution of Public Keys, Kerberos, X.509 Authentication
Service, Public – Key Infrastructure, overview of SSL/TLS.

Suggested Books:
1. Cryptography and Network Security: Forouzan Mukhopadhyay, Mc Graw Hill, 1 st
and 2nd Edition.
2. Katz and Y. Lindell, Introduction to Modern Cryptography, CRC press, 2020. 1 st and
4th Edition
3. Cryptography and Network Security - Principles and Practice: William Stallings,
Pearson Education, 6th Edition
OE-CS- Network Operating System
AIML-406
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
3 0 0 3 75 25 100 3 Hr.
Course Outcomes
CO1 To Identify the features of modern Microsoft operating systems including
UNIX and UNIX-like operating systems.

CO2 To Explain the fundamentals of operating system and its use in network
communication.
CO3 To Analyze how to manage user accounts, group accounts, and shared
resources.
CO4 To Devise a security policy for your client and server computers.

Unit-1

Computer basics—Understanding operating systems, Fundamentals of operating systems,


Functions of operating system,Types, Resource Management, Operating system basics

Unit-2

Modern Client and Server Operating Systems, client server model, Concepts of Linux, OS
Alternatives and Recommendations, Account and Resource Management
Unit-3

Central processing unit (CPU), file system, Types of Computer File Systems and How They
Work, Examples, Linux File System/Structure, Understanding active directory and group
policy

Unit-4
Network operating system, Types of operating system, Network Fundamentals and
Configuration, The Next Platform - one network operating system to unite them all, Securing
and Maintaining an Operating System

References:
1. GCF Global. (n.d.). Computer basics—Understanding operating systems.
2. Operating system by Galvin
3. Computer Networks by Andrew S. Tanenbaum,1981
4. Kindson the Tech Pro. (2020, October 2). Windows Server 2019 Administration
Complete Course – 2020
5. Kottayil, N.K. (2020, August 14). Central processing unit (CPU). Techopedia.
OE-CS- Reasoning, Problem Solving and Robotics
AIML-408
L T P Credit Major Test Minor Test Total Time
3 0 0 3 75 25 100 3 Hour
Purpose The course provides grounding in basic and advanced method how to
solve problem
Course Outcomes –At the end of this course students will be able to:
CO1 To list and explain the basic elements of robots
CO2 To analyze robot kinematics and its control methods
CO3 To Classify the various sensors used in robots for better performance
CO4 To summarize various industrial and non-industrial applications of robots
UNIT-I

Introduction to Robot- Basic concepts, Need, Law, History, Anatomy, specifications. Robot
configurations- Cartesian, cylinder, polar and articulate. Robot wrist mechanism, Precision
and accuracy of robot.

UNIT-II

End Effectors-Classification, Types of Mechanical actuation, Gripper design, Robot drive


system Types, Position and velocity feedback Devices-Robot joints and Links-Types, Motion
interpolation. Robot kinematics – Basics of direct and inverse kinematics, Robot trajectories,
2D and 3D Transformation-Scaling, Rotation, Translation Homogeneous transformation.

UNIT-III

Sensors in robot – Touch Sensors-Tactile sensor – Proximity and range sensors. Force
Sensor-Light sensors, Pressure sensors, Introduction to Machine Vision and Artificial
Intelligence

UNIT-IV

Control of robot manipulators – Point to point, Continuous Path Control, Robot


programming. applications of robots, Medical, Household, Entertainment, Space,
Underwater, Defense, Disaster management. Applications, Micro and Nanorobots, Future
Applications.

Reference Book:

1. Mikell P. Groover, Mitchell Weiss, Roger N Nagel, Nicholas G Odrey, “Industrial


Robotics Technology, Programming and Applications”, Tata –McGraw Hill Pub. Co., 2008.
Half 1st
2. Deb.S.R and Sankha Deb, "Robotics Technology and Flexible Automation", Tata McGraw
Hill Publishing Company Limited, 2010. 1st and 4th Edition
3. Klafter.R.D, Chmielewski.T.A, and Noggin’s., “Robot Engineering: An Integrated
Approach”’, Prentice Hall of India Pvt. Ltd., 1994. 3rd Edition
4. Fu.K.S, Gonzalez.R.C&Lee.C.S.G, “Robotics control, sensing, vision and intelligence”,
Tata- McGraw Hill Pub. Co., 2008
5. Yu. “Industrial Robotics”, MIR Publishers Moscow, 1985.
OE-CS-
AIML- Image Processing and Recognition
410

Lecture Tutorial Practical Credit Major Minor Total Time


Test Test

3 0 0 3 75 25 100 3 Hrs.

Purpose To imparts knowledge in the area of image and image processing, fundamentals
of digital image processing and also to learn the fundamentals of pattern
recognition and to choose an appropriate feature.

Course Outcomes

CO 1 To Understand Basics of Image formation and transformation using sampling


and quantization

CO 2 To Understand different types signal processing techniques used for image


sharpening and smoothing

CO 3 To understand the nature and inherent difficulties of the pattern recognition


problems.

CO 4 Understand concepts, trade-offs, and appropriateness of the different feature


types and classification techniques such as Bayesian, maximum likelihood, etc

Unit-I
Introduction to image processing and restoration, Image formation, image geometry
perspective and other transformation, stereo imaging elements of visual perception. Digital
Image-sampling and quantization serial & parallel Image processing, Image Restoration-
Constrained and unconstrained restoration Wiener filter, Motion blur remover.

Unit-II

Segmentation Techniques-thresh holding approaches, region growing, relaxation, line and


edge detection approaches, edge linking, supervised and unsupervised classification
techniques, remotely sensed image analysis and applications, Shape Analysis – Gestalt
principles, shape number, moment Fourier and other shape descriptors, Skelton detection.
Unit-III

Pattern Recognition, Basics of pattern recognition, Design principles of pattern recognition


system, Learning and Adaption, Pattern recognition approaches,Mathematical Foundation-
Linear Algebra, Probablity theory, Expectation, mean, covariance,NormalDistribution,
Multivariate normal densities, chi square test.
Bayesian Decision Theory, Classifiers, Normal density and discriminant functions, Parameter
estimation methods: Maximum-Likelihood estimation, Bayesian Parameter estimation

Unit-IV

Statistical pattern recognition: Dimension reduction methods – Principal Component


Analysis (PCA), Fisher Linear discriminant analysis, Expectation-maximization (EM),
Hidden Markov Models (HMM), Gaussian mixture models.

Suggested Books

1. Digital Image Processing – Ganzalez and Wood, Addison Wesley, 1993.


2. Fundamental of Image Processing – Anil K.Jain, Prentice Hall of India.
3. Pattern Classification – R.O. Duda, P.E. Hart and D.G. Stork, Second Edition John
Wiley, 2006
4. An Introduction to Digital Image Processing – Wayne Niblack, Prentice Hall, 1986
5. Pattern Recognition and Machine Learning – C. M. Bishop, Springer, 2009.
6. Pattern Recognition – S. Theodoridis and K. Koutroumbas, 4th Edition, Academic
Press,2009
PE-CS- Reinforcement Learning
AIML-
402A

L T P Credit Major Test Minor Test Total Time

2 0 0 2 75 25 100 3 hrs.

Purpose Purpose To provide knowledge of various Reinforcement Learning Algorithms

Course Outcomes (CO)

CO 1 To learn the basics of Reinforcement Learning concepts, various Reinforcement


Learning architecture
CO 2 To explore knowledge of various process of Reinforcement Learning

CO 3 To understand the basics of Reinforcement Learning models

CO 4 To implies about the different Reinforcement Learning algorithms and their


applications to solve real world problems.
UNIT-1

Introduction to Reinforcement Learning: Origin and history of Reinforcement Learning


research. Its connections with other related fields and with different branches of machine
learning, The Reinforcement Learning Process Elements of Reinforcement Learning RL
Agent Taxonomy Reinforcement Learning Problem.

Unit-II

Markov Decision Process: Introduction to RL terminology, Markov property, Markov chains,


Markov reward process (MRP). Introduction to and proof of Bellman equations for MRPs
along with proof of existence of solution to Bellman equations in MRP. Introduction to
Markov decision process (MDP), state and action value functions, Bellman expectation
equations, optimality of value functions and policies, Bellman optimality equations.

Unit-III

Monte Carlo Methods for Model Free Prediction and Control: Overview of Monte Carlo
methods for model free RL, First visit and every visit Monte Carlo, Monte Carlo control, On
policy and off policy learning, Importance sampling.
TD Methods Incremental Monte Carlo Methods for Model Free Prediction, Overview TD (0),
TD (1) and TD(λ), k-step estimators, unified view of DP, MC and TD evaluation methods,
TD Control methods - SARSA, Q-Learning and their variants.

Unit-IV

Function Approximation Methods: Getting started with the function approximation methods,
Revisiting risk minimization, gradient descent from Machine Learning, Gradient MC and
Semi-gradient TD (0) algorithms, Eligibility trace for function approximation, Afterstates,
Control with function approximation, least squares, Experience replay in deep Q-Networks

Suggested Book: Richard S. Sutton and Andrew G. Barto “An Introduction to Reinforcement
Learning Enes Bilgin “ Mastering Reinforcement Learning with Python: Build next-
generation, self-learning models using reinforcement learning techniques and best practices”
1st Edition Kindle
PE-CS-AIML-
Social Networks
416A
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
2 0 0 2 75 25 100 3 Hour
Purpose Students will be able to use Social networks for business and personal use,
conducting social network analysis, social network developer tools and social
network concepts for solving real-world issues.
Course Outcomes (CO)
CO1 To Demonstrate proficiency in the use of social networks for business and
personal use
CO2 To Demonstrate proficiency in the use of social network analysis concepts
and techniques.
CO3 To Demonstrate proficiency in the use of social network developer tools.
CO4 To Examine the various types of processors and demonstrate proficiency in
the use of social network concepts for solving real world issues.

Unit-1

Introduction to Semantic Web: Limitations of current Web - Development of Semantic Web -


Emergence of the Social Web - Social Network analysis: Development of Social Network
Analysis - Key concepts and measures in network analysis - Electronic sources for network
analysis: Electronic discussion networks, Blogs and online communities - Web-based
networks - Applications of Social Network Analysis.

Unit-2

Ontology and their role in the Semantic Web: Ontology-based knowledge Representation -
Ontology languages for the Semantic Web: Resource Description Framework - Web
Ontology Language - Modeling and aggregating social network data: State-of-the-art in
network data representation - Ontological representation of social individuals - Ontological
representation of social relationships - Aggregating and reasoning with social network data -
Advanced representations.

Unit-3

Extracting evolution of Web Community from a Series of Web Archive - Detecting


communities in social networks - Definition of community - Evaluating communities -
Methods for community detection and mining - Applications of community mining
algorithms - Tools for detecting communities social network infrastructures and
communities - Decentralized online social networks.

Unit-4

Understanding and predicting human behavior for social communities - User data
management - Inference and Distribution - Enabling new human experiences - Reality mining
- Context - Awareness - Privacy in online social networks - Trust in online environment -
Trust models based on subjective logic - Trust network analysis.
TEXT BOOKS:
1. Peter Mika, Social Networks and the Semantic Web‖, First Edition, Springer 2007.
2. BorkoFurht, Handbook of Social Network Technologies and Applications, 1st Edition,
Springer, 2010.

REFERENCES
1. GuandongXu ,Yanchun Zhang and Lin Li, Web Mining and Social Networking
Techniques and applications‖, First Edition, Springer, 2011.
2. Dion Goh and Schubert Foo, Social information Retrieval Systems: Emerging
Technologies and Applications for Searching the Web Effectively‖, IGI Global
Snippet, 2008.
PE-CS-AIML- Neural Network and Fuzzy Logic systems
420A
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
2 0 0 2 75 25 100 3Hr.
Course Outcomes
CO1 To The course is designed to give a solid grounding of fundamental concepts of
fuzzy logic and its applications. The level of the course is chosen to be such that
all students aspiring to be a part of computational intelligence directly or
indirectly in near future should get a foundation of these concepts through this
course.

CO2 To Understanding reasoning and fuzzy logic for artificial intelligence

CO3 To Students will be able to learn defuzzification and fuzzy measures

CO4 To
studentswillbeabletolearntheapplicationsoffuzzylogicandhybridsoftcomputingtec
hniques

Unit-I
Neural Networks-I (Introduction & Architecture): Neuron, Nerve structure and synapse,
Artificial Neuron and its model, activation functions, Neural network architecture: single
layer and multilayer feed forward networks, Auto-associative and hetro-associative memory.
Neural Networks-II Back propagation network Architecture, back propagation learning
methods,Applications of Artificial Neural Networks- Social Media, Marketing and Sales,
Healthcare, Personal Assistants.

Unit II
Uncertainty in information, Fuzzy sets and membership, Chance versus ambiguity, Fuzzy set
vs. Crisp set, Classical sets – operations on classical sets, Fuzzy sets – fuzzy set operations,
Properties of fuzzy sets. A brief history of Fuzzy logic, Fuzzy logic vs. Crisp logic, Concept
of fuzzy system, Concept of fuzzy set, Examples of fuzzy set, Some basic terminologies and
notations for fuzzy sets.
Unit III
Fuzzy Membership Functions, Operations on Fuzzy Sets, Fuzzy Relations, Rules and
Inferences, Fuzzy Relations, Crisp relations, Operations on crisp relations, Composition of
two crisp relations, Operations on Fuzzy relations, Fuzzy Propositions, Fuzzy Implications,
Fuzzy Inferences, Generic structure of a Fuzzy system, Defuzzification Techniques, Lambda-
cut method, Weighted average method, Maxima methods, Centroid methods

Unit IV
Problems in some areas of applications: Medical diagnosis, Person identification / Computer
vision, Handwritten character recognition, Pattern recognition and Machine Intelligence (MI),
Weather forecasting, VLSI design, Network optimization, Fuzzy Systems: Fuzzy Logic
Control System, Industrial applications

References:
1. Kliryvan- FuzzySystem&FuzzylogicPrenticeHallofIndia, FirstEdition.
2. LawrenceFussett-fundamental of Neural Network Prentice Hall, First Edition and 4th
Edition
3. Bart Kosko, “NeuralnetworkandFuzzySystem”-PrenticeHall Pub.-1994.
4. Fuzzy Logic: A Practical approach, F. Martin, , Mc neill, and Ellen Thro, AP
Professional, 2000.
5. Fuzzy Logic with Engineering Applications (3rd Edn.), Timothy J. Ross, Willey,
2010.
6. Foundations of Neural Networks, Fuzzy Systems, and Knowldge Engineering,
Nikola K. Kasabov, MIT Press, 1998.
7. Fuzzy Logic for Embedded Systems Applications, Ahmed M. Ibrahim, Elesvier Press,
2004.Education
PE-CS-AIML- Augmented Reality
422A
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
2 0 0 2 75 25 100 3Hr.
Course Outcomes
CO1 The course is designed to describe how VR systems work and list the applications of VR.

CO2 Understand the design and implementation of the hardware that enables VR systems tobe
built
CO3 Understand the system of human vision and its implication on perception and rendering

CO4 Explain the concepts of motion and tracking in VR systems and Describe the importance of
interaction and audio in VR systems

Unit I

Introduction to Augmented Reality (A.R): What Is Augmented Reality: - Introduction to AR,


History of AR, Purpose of AR, Relation Between AR and other Technology, Application of
AR, How AR work, Scope of AR, overview of AI in AR

Unit II:

Augmented Reality Hardware

Displays: - Audio Displays, Haptic Displays, Visual Displays, Other sensory displays, Visual
Perception, Requirements and Characteristics.

Processors: - Role of Processors, Processor System Architecture, Processor Specifications.

Tracking & Sensors: - Tracking, Calibration, and Registration, Characteristics of Tracking


Technology, Stationary Tracking Systems, Mobile Sensors, Optical Tracking, Sensor Fusion.

Unit III:

Computer Vision for Augmented Reality & A.R. Software

Computer Vision for Augmented Reality: - Marker Tracking, Multiple-Camera Infrared


Tracking, Natural Feature Tracking by Detection, Simultaneous Localization and Mapping,
Outdoor Tracking

Augmented Reality Software: - Introduction, Major Software Components for Augmented


Reality Systems, Software used to Create Content for the Augmented Reality Application.

Unit IV:

AR Techniques- Marker based & Marker-less tracking

Marker-based approach: - Introduction to marker-based tracking, types of markers, marker


camera pose and identification, visual tracking.

Marker types: -Template markers, 2D barcode markers, imperceptible markers.


Marker-less approach: -Localization based augmentation, real world examples.

Tracking methods: -Visual tracking, feature based tracking, hybrid tracking, and initialisation
and recovery.

Text Books:

1. Virtual Reality, Steven M. LaValle, Cambridge University Press, 2016

2. Understanding Virtual Reality: Interface, Application and Design, William R Sherman and Alan B
Craig, (The Morgan Kaufmann Series in Computer Graphics)”. Morgan Kaufmann Publishers, San
Francisco, CA, 2002

3. Developing Virtual Reality Applications: Foundations of Effective Design, Alan B Craig, William
R Sherman and Jeffrey D Will, Morgan Kaufmann, 2009.

Reference Books:

1. Gerard Jounghyun Kim, “Designing Virtual Systems: The Structured Approach”, 2005.

2. Doug A Bowman, Ernest Kuijff, Joseph J LaViola, Jr and Ivan Poupyrev, “3D User Interfaces,
Theory and Practice”, Addison Wesley, USA, 2005.

3. Oliver Bimber and Ramesh Raskar, “Spatial Augmented Reality: Meging Real and Virtual
Worlds”, 2005.

4. Burdea, Grigore C and Philippe Coiffet, “Virtual Reality Technology”, Wiley Interscience, India,
2003.
PE- CS- AIML- Advance Machine Learning
424A
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
2 0 0 2 75 25 100 3 Hr.
Course Outcomes
CO1 To understand advanced methods of machine learning.

CO2 To Emphasis on approaches of deep learning with practical relevance.


CO3 To Analyze recent applications of advanced machine learning.
CO4 To Understand implementation of advanced machine learning.
UNIT-I

Binary Classification, Logistic Regression, Gradient Descent, Derivatives, Computation


graph, Vectorization, Vectorizing logistic regression – Shallow neural networks: Activation
functions, non-linear activation functions,

UNIT-II

Deep Neural Networks: Deep L-layer neural network, Forward and Backward propagation,
Deep representations, Parameters vs Hyperparameters, building a Deep Neural Network
(Application) – Supervised Learning with Neural Networks – Practical aspects of Deep
Learning: Train/Dev / Test sets, Bias/variance, Overfitting and regularization, Linear models
and optimization, Vanishing/exploding gradients, Gradient checking – Logistic Regression.

UNIT-III
Back-propagation: architecture, training algorithm, selection of parameters, learning
application algorithm, local and global minima, merits and demerits, application.
Optimization algorithms: Mini-batch gradient descent, exponentially weighted averages,
RMSprop, Learning rate decay, problem of local optima, Batch norm – Parameter tuning
process.

UNIT-IV
Convolution Neural Networks: introduction, architecture, padding, strided convolutions,
pooling layers, ResNet, MobileNet, applications of CNN, Recurrent Neural Network:
Expressiveness of recurrent networks, Architecture, Challenges of training Recurrent
networks, Long short-term memory, Gated recurrent units, Applications of RNNs. Self-
Organizing Maps, Restricted Boltzmann Machines.

References:
1. Deep Learning, Ian Goodfellow, YoshuaBengio and Aeron Courville, MIT Press,First
Edition, 2016.
2. Deep Learning, A practitioner’s approach, Adam Gibson and Josh Patterson, O’Reilly,
First Edition, 2017.
3. Hands-On Learning with Scikit-Learn and Tensorflow, AurelienGeron, O’Reilly, First
Edition, 2017.
4. Deep Learning with Python, Francois Chollet, Manning Publications Co, First Edition,
2018.
5. Python Machine Learning by Example, Yuxi (Hayden) Liu, First Edition, 2017.
6. A Practical Guide to Training Restricted Boltzmann Machines, Geoffrey Hinton, 2010,
PE-CS-AIML- Natural Language Processing
426A
Lecture Tutorial Practical Credit Major Minor Total Time
Test Test
2 0 0 2 75 25 100 3Hrs.
Purpose Toprovidetheunderstandingofthemathematicalandlinguisticfoundationsunderl
yingapproachestothe various areas inNLP.
Course Outcomes(CO)
CO1 Be familiar with syntax and semantics in NLP.
CO2 To implement various concepts of knowledge representation using Prolog.
CO3 To classify different parsing techniques and understand semantic networks.
CO4 To identify/explain various applications of NLP.

Unit-I
Basic Concepts: concept overview, Intro to NLP, history of NLP, Applications of NLP
Key algorithms in the noisy channel paradigm. Fundamental components of Natural
Language Processing: Lexicography, syntax, semantics, prosody, phonology, pragmatic
analysis, world knowledge.
Knowledge Representation schemes: Semantic net, Frames, Conceptual Dependency, Scripts.

Unit-II
Representing knowledge using rules: Logic Programming, Introduction to LISP and Prolog,
Rules based deduction systems, General concepts in knowledge acquisition.
Syntax Analysis: Formal Languages and grammars, Chomsky Hierarchy, Left- Associative
Grammars, ambiguous grammars, resolution of ambiguities.

Unit-III
Computation Linguistics: Recognition and parsing of natural language structures- ATN and
RTN, General Techniques of parsing-CKY, Earley and Tomitas algorithm. Semantics:
Knowledge representation, semantics networks logic and inference pragmatics, graph models
and optimization.

Unit-IV
Applications of NLP: Intelligent work processor, Machine translation, user interfaces, Man-
Machine interfaces, natural language querying, tutoring and authoring systems, speech
recognition, commercial useof NLP.

References Books:
1. Daniel Jurafsky, James H. Martin, “Speech and Language Processing: An
Introduction to Natural Language Processing, Computational Linguistics and Speech
Recognition”, 2nd edition, Pearson Edu., 2013.
2. James Allen, “Natural Language Understanding”, Pearson Education, Second Edition,
2003
3. Ivan Bratko, “Prolog: Programming for Artificial Intelligence”, 3rd Edition, Pearson
PC-CS- Optimization Lab
AIML-406LA
Lecture Tutorial Practical Credit Minor Practical Total Time
Test
0 0 2 1 40 60 100 3 Hrs.
Purpose To Understand and implement various optimization methods in machine learning

Course Outcomes-At the end of this course students will be able to:
CO1 Apply mathematical and computational skills needed for the practical utility
operation research.
CO2 Implement various linear programming problems

CO3 Implement various optimization methods in machine learning


CO4 Understand and implement genetic algorithms
Education, Fifth Impression 2009.
4. G. Gazder, “Natural Language processing in prolog”, Addison Wesley, 1989.

List of experiments:

1. Write a python program to solve the linear problem:

Minimize: Z = 3x + 5y
Subject to the constraints:
2x + 3y >= 12
-x + y <= 3
x >= 4
y <= 3
x, y >= 0
2. Write a program in python to find the EVD (Eigen Value Decomposition) of A,
where

3. Write a program in python to find the SVD (Singular Value Decomposition) of A,


UΣV T, where

4. Write a program to implement Second Order Cone Program (SOCP).


5. Write a program to demonstrate KKT conditions.
6. Write a program to implement gradient Descent algorithm for finding local minima.
7. Write a program to implement Frank-Wolfe algorithm.
8. Write a program to implement Stochastic Gradient Descent Algorithm.
9. Write a program to create target string starting from random string using Genetic
Algorithm.
10. Write a program to implement Particle Swarm optimization to find optimal solution.
PC- CS- Advance AI Application Lab
AIML-
408LA
Lecture Tutorial Practical Credit Minor Practical Total Time
Test
0 0 2 1 40 60 100 3 Hrs.
Purpose To Understand and implement various artificial intelligence

Course Outcomes
CO1 Implementation of various type of algorithm in AI applications for better use of
application
CO2 In-depth learning of machine learning, Deep learning and neural networks

CO3 Implement various artificial intelligence technique


CO4 Understand artificial intelligence and its analytics in real world

List of Experiments:

1. Chat bot
2. Music Recommendation App
3. Stock Prediction
4. Social Media Suggestion
5. Lane line detection while driving
6. Monitoring crop health
7. Medical diagnosis
8. AI powered Search engine
9. AI powered cleaning robots

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy