B.M.S.

College of Engineering, Bengaluru – 19

(Autonomous Institute, Affiliated to VTU | Approved by AICTE)
Scheme of Instructions Semester – VII (With effect from the Academic Year 2022-23: Admitted batches and onwards)
Teaching Hrs.
Examination
In Credits/Week

Total Credits

Total Marks
SEE Marks
CIE Marks
Practical
Tutorial
Course

Duration
Lecture
Theory
Sl. # Course Code Course Title

in Hrs.
Type

L T P
1 PC-20 24AM7PCTSA Time Series Analysis 2 0 1 3 4 50 50 100
2 PC-21 24AM7PCLLM Natural Language Processing for LLM 2 0 0 2 2 50 50 100
24AM7PEVCV Video Analytics using OpenCV
3 24AM7PESNA Social Network Analysis
PE-3 3 0 0 3 3 50 50 100
24AM7PECYS Cyber Physical Systems
24AM7OEAIG Introduction to AI
OE-2 24AM7OEMLG Introduction to Machine Learning
4 3 0 0 3 3 50 50 100
24AM7OEINN Introduction to Neural Networks

5 PW-3 24AM7PWPW2 Project work-2 0 0 4 4 8 50 50 100

6 HS-5 25MA7HSIKL Indian Knowledge Systems 1 0 0 1 1 50 50 100
Details of 80 AICTE Activity Points Earned

Total 11 0 5 16 22 250 250 500

Note: HS: Humanities and Social Sciences/Management Course, BS: Basic Science Course, ES: Engineering Science Course, PC: Professional Core Course, PE: Professional
Elective Course, OE: Open Elective Course; PW: Project/Mini Project Work, INT: Seminar on Internship, AE: Ability Enhancement Course / Mandatory Course,
NCMC: Non-credit mandatory course
 Course Title TIME SERIES ANALYSIS
Course Code 24AM7PCTSA Credits 3 L-T-P 2-0-1
CIE 50 Marks SEE 100 Marks (50% Weightage)
Contact Hours / Week 4 Total Lecture Hours 26

UNIT – 1 5 Hrs
Introduction to Time Series: Additive and Multiplicative Models, Time series
components – Trend, Seasonal, Cyclical and Irregular Components. Measuring Trend:
Graphic, Semi-Averages, Moving Average and Least Squares Method. Measuring Seasonal
Variations - Simple Averages, Ratio-Trend Method, Ratio-Moving Average Method and
Link Relative Method.
UNIT – 2 5 Hrs
Forecasting Techniques: Moving Average Models - Simple and Weighted Moving
Average, Exponential Smoothening – Simple Exponential Smoothing (SES), Double
Exponential Smoothing (Holt Method), Holt-Winters Smoothing.
UNIT – 3 5 Hrs
Stationary Time Series Models: White noise, Stationary Process, The autocorrelation
function, The partial autocorrelation function, AR Process, MA Process, ARMA Process.
UNIT – 4 5 Hrs
Non-Stationary Time Series Models: The random walk process, Indicators of Non-
Stationarity: Time series graphs, ACF Plots, Dicky Fuller Unit Root Test, ARIMA Model,
SARIMA Model. Transforming a non-stationary series into a stationary series: differencing
the series (or de-trending), log transformation.
UNIT – 5 6 Hrs
Time Series Models of Heteroscedasticity: Homoscedasticity and Heteroscedasticity,
some common features and applications of Financial Time Series, ARCH Model, GARCH
Model: Model Identification using ACF and PACF Plots and EACF Table, Testing for ARCH
Effects: Visual inspection of time series and residual plots, the ARCH-LM Test, Identifying
an ARCH/GARCH Model in practice, Maximum Likelihood Estimation.
Text Books:
1. Introduction to Time Series Analysis and Forecasting, Douglas C. Montgomery, Cheryl
L. Jennings, Murat Kulahci, 2nd Edition, Wiley, 2015.
2. Time Series Analysis and Forecasting by Example, Søren Bisgaard, Murat Kulahci,
Wiley, 2011.
Reference Books:
1. Hands-On Time Series Analysis with R, Rami Krispin, Packt Publishing Ltd, 2019.
2. Time Series Analysis with Applications in R, Jonathan D. Cryer & Kung-Sik Chan, 2nd
Edition, Springer, 2008.
Course Outcomes
Apply effective techniques on time-dependent information to construct predictive models
CO1
and facilitate decision-making processes.
Develop skills in identifying appropriate time series models by utilizing a range of diagnostic
CO2
tools and statistical inference techniques.
CO3 Develop time series and financial models tailored for real-time applications.
CO-PO-PSO Mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PS01 PS02 PS03
CO1 2 3 2 2
CO2 3 2 2
CO3 2 2 2 2

Massive Open Online Course (MOOC)

Sl. Course Offered Course Link
No. by
1 Applied Time- IIT [Link]
Series Analysis Madras
2 Practical Time
Coursera [Link]
Series Analysis

Semester End Examination (SEE) Question Paper Pattern:

UNIT # Internal Choice/ Unit Wise Marks Distribution

Mandatory

Unit 1 Mandatory One question to be asked for 20 marks each

Unit 2 Mandatory One question to be asked for 20 marks each

Unit 3 Mandatory One question to be asked for 20 marks each

Unit 4 Internal Two questions to be asked for 20 marks each

Choice
Unit 5 Internal Two questions to be asked for 20 marks each
Choice

Percentage of Questions to be included in SEE

Bloom’s Level
QuestionPaper
Remember / Understand 25%

Apply / Analyze 55%

Create / Evaluate 20%

Assessment Pattern
Category Score Split up Total
CIE – 1
Continuous Theory 40 M 50M
Internal CIE – 2 (Best of Two)
Assessment(CIE) CIE – 3
AAT 05M
Quiz 05M
Semester End
Examination 100M (50% weightage) 50M
(SEE)
Total 100M
Lab Topics:
SI No. Topics
Introduction to Time Series in Python: Loading the data, Examining the data,
1
Plotting the Data.
2 Forecasting Techniques.
White Noise, Random Walk, Stationarity: Determining Weak Form of
3
Stationarity.
4 Determining Trend, Seasonality, ACF and PACF Plot.
The AR Model- Examining the ACF and PACF plots, Fitting AR (1) Model,
5 Fitting Higher Lag AR Models.
The MA Model- Examining the ACF and PACF plots, Fitting MA (1) Model,
6
Fitting Higher Lag MA Models.
The ARMA Model: Examining the ACF and PACF plots, Fitting ARMA (1,1)
7
Model, Fitting Higher Lag ARMA Models.
8 The ARIMA Model: Fitting ARIMA Model.
9 The ARCH Model.
10 The GRACH Model.
 Course Title NATURAL LANGUAGE PROCESSING FOR LLM
Course Code 24AM7PCLLM Credits 2 L-T-P 2-0-0
100 Marks (50%
CIE 50 Marks SEE
Weightage)
Contact Hours / Week 2 Total Lecture Hours 26

UNIT – 1 5 Hrs
Introduction: What is Natural Language Processing (NLP), Origins of NLP, Phases of NLP,
Ambiguities in NLP- Why is NLP hard? Applications of [Link] Preprocessing: Regular
Expressions, Text Normalization, Tokenization- Byte Pair Encoding, Word piece,
sentence piece, Lemmatization, Stemming.
UNIT – 2 5 Hrs
Text Representation: Lexical Semantics, Vector Semantics, Words and Vectors, Cosine
for measuring similarity, TF-IDF: Weighing terms in the vector, Pointwise Mutual
Information (PMI), word embeddings: Static word embedding, Contextual embeddings.
Parsing: Constituency Parsing, Dependency Parsing: Transition-Based Dependency
Parsing.
UNIT – 3 5 Hrs
Language Modeling: Types of language models, Statistical Language Model: N-grams. Pre
trained Language Models: BERT, RoBERTa, ALBERT, ELECTRA, XLNet.
Generative AI : Generative AI & LLMs, Transformers Architecture: A Self- Attention
Network, Multihead Attention, Understanding the key components and its role in language
generation. Prompt Engineering and Instruction Fine-Tuning: Techniques to guide LLMs
in generating desired outputs ,Parameter Efficient Fine-Tuning (PEFT) for optimized
model adaptation.
UNIT – 4 6 Hrs
Reinforcement Learning with Human Feedback: Enhancing LLM performance through
human interaction. RLHF: Reward model, RLHF: Fine-tuning with reinforcement learning,
Proximal policy optimization, RLHF: Reward hacking, Scaling human feedback. Retrieval-
Augmented Generation (RAG) and its potential .Case Studies: LLM-powered Applications.
UNIT – 5 5 Hrs
Model optimizations for deployment: Generative AI Project Lifecycle: Revisited ,
Helping LLMs reason and plan with chain-of-thought, Program-aided language models
(PAL), ReAct : Combining reasoning and action,LangChain: Framework for developing
applications using LLMs ,Training & Deployment Strategies for LLMs. Responsible Al in
Generative Al: Ethical considerations and mitigating [Link] Cases & Case Studies:
Real-world applications of Generative Al and LLMs.
Text Books:
1. Speech and Language Processing: An introduction to Natural Language Processing,
Computational Linguistics and Speech Recognition, Daniel Jurafsky, James H Martin,
3rd Edition, Prentice Hall, 2024.
2. Natural Language Processing: An Information Access Perspective, Kavi Narayana
Murthy, Ess Ess Publications, 2006.
Reference Books:
1. Natural Language Processing with Transformers: Building Language Applications
 with Hugging Face, Lewis Tunstall, Leandro von Werra, Thomas Wolf, O'Reilly
Media, Inc, 2022.
2. Applied Text Analysis with Python, Benjamin Bengfort, Tony Ojeda, Rebecca Bilbro,
O'Reilly Media, 2018.

Course Outcomes
Apply foundations of natural language processing in linguistics and formal language
CO1
theory to build NLP applications.
CO2 Analyze NLP tasks using existing algorithms.

CO3 Conduct experiments to implement building blocks of NLP.

CO – PO - PSO Mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 2 2
CO2 3 2 2
CO3 2 3 2

Massive Open Online Course (MOOC)

Sl.
Course Offered by Course Link
No.
1. Natural Language
NPTEL [Link]
Processing
2. Natural Language
[Link]
Processing Coursera
language-processing
Specialization
3. Applied Natural
Language NPTEL [Link]
Processing

Semester End Examination (SEE) Question Paper Pattern:

Internal Choice /
UNIT # Unit Wise Marks Distribution
Mandatory
Unit 1 Mandatory One question to be asked for 20 marks

Unit 2 Mandatory One question to be asked for 20 marks

Unit 3 Internal Choice Two questions to be asked for 20 marks each

Unit 4 Internal Choice Two questions to be asked for 20 marks each

Unit 5 Mandatory One question to be asked for 20 marks

Percentage of Questions to be included in SEE

Bloom’s Level
Question Paper
Remember / Understand 25%

Apply / Analyze 50%

Create / Evaluate 25%

Assessment Pattern:
Category Score Split up Total
CIE - 1 40M
Continuous Internal CIE – 2 (Best of Two)
Theory 50M
Evaluation (CIE) CIE - 3
AAT/Quiz 10M
Semester End
100M (50% weightage) 50M
Examination (SEE)
Total 100M
 Course Title VIDEO ANALYTICS USING OPENCV
Course Code 24AM7PEVCV Credits 3 L-T-P 3-0-0
CIE 50 Marks SEE 100 Marks (50% Weightage)
Contact Hours / Week 3 Total Lecture Hours 36

UNIT – 1 7 Hrs
Introduction to Video Analytics: Basics of Video Analytics, Video IO using OpenCV,
Frame Differencing, Background Subtraction Technique-Mixture of Gaussians, K-Nearest
Neighbours, Introduction to Optical Flow-Lucas-kanade, Ferback method.
UNIT – 2 7 Hrs
Motion Detection and Tracking: Motion Detection Techniques, Object Tracking
Algorithms MeanShift, CamShift, Kalman Filter for Tracking, Multiple Object Tracking-Data
Association, Joint Probabilistic Data Association, Multiple hypothesis tracking,
Applications of Motion Tracking.
UNIT – 3 7 Hrs
Video Stabilization: Basics of Video Stabilization: Stabilization pipeline, Types of
stabilization Motion Estimation Techniques: Block matching, Optical flow, Feature
matching, Global Motion Compensation, Video Stabilization using OpenCV, Applications of
Video Stabilization.
UNIT – 4 8 Hrs
Action Recognition and Event Detection: Basics of Action Recognition, Key Frame
Extraction :Shot Boundary detection, clustering, Saliency based methods, Temporal
Feature Extraction, Machine Learning Techniques for Action
Recognition:SVM,CNN,RNN,3D RNN, Applications of Event Detection.
UNIT – 5 7 Hrs
Video Analytics Applications: Video Surveillance Systems: Motion detection, object
tracking, anomaly detection, real time processing. Traffic Monitoring and Analysis, Face
Detection and Recognition in Videos, Gesture Recognition, Applications of Video Analytics
in Smart Cities.
Text Books:
1. Computer Vision: Algorithms and Applications, Richard Szeliski. A free electronic
copy is available online (Link).
2. Learning OpenCV 3: Computer Vision in C++ with the OpenCV Library, Adrian
Kaehler and Gary Bradski.
3. Practical Computer Vision with OpenCV , Abhinav Dadhich
Reference Books:
1. Introductory techniques for 3-D Computer Vision, Emanuele Trucco and
Alessandro Verri.
2. Multiple View Geometry in Computer Vision, Richard hartley and Andrew
Zisserman, 2nd Edition.
3. Computer Vision: A Modern Approach, David Forsyth and Jean Ponce.
4. Digital Image Processing, Rafael Gonzalez, Richard Woods.
5. Deep Learning for Computer Vision, Rajalingappaa Shanmugamani.
6. Computer Vision: Algorithms and Applications, by Richard Szeliski.

Course Outcomes
Apply the basic concepts of computer vision and video analytics in processing images
CO1
and videos.
 Analyze the key features of OpenCV library to perform video input/output
CO2
operations.
Develop video analytics techniques to real-world problems such as surveillance, traffic
CO3
analysis, and activity recognition.

CO – PO - PSO Mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 1 2
CO2 2 2
CO3 2 2

Massive Open Online Course (MOOC)

Sl.
Course Offered by Course Link
No.
1. OpenCV Crash Course OpenCV [Link]
2. Computer Vision NPTEL [Link]

Semester End Examination (SEE) Question Paper Pattern:

Internal Choice /
UNIT # Unit Wise Marks Distribution
Mandatory
Unit 1 Mandatory One question to be asked for 20 marks

Unit 2 Internal Choice Two questions to be asked for 20 marks each

Unit 3 Mandatory One question to be asked for 20 marks

Unit 4 Internal Choice Two questions to be asked for 20 marks each

Unit 5 Mandatory One question to be asked for 20 marks

Percentage of Questions to be included in SEE

Bloom’s Level
Question Paper
Remember / Understand 25%

Apply / Analyze 50%

Create / Evaluate 25%

Assessment Pattern:
Category Score Split up Total
CIE - 1
40M
CIE – 2 (Best of Two)
Continuous Internal Evaluation (CIE) Theory 50M
CIE - 3
AAT/Quiz 10M
Semester End Examination (SEE) 100M (50% weightage) 50M
Total 100M
 Course Title SOCIAL NETWORK ANALYSIS
Course Code 24AM7PESNA Credits 3 L-T-P 3-0-0
CIE 50 Marks SEE 100 Marks (50% Weightage )
Contact Hours /Week 3 Total Lecture Hours 36

UNIT – 1 8 Hrs
Introduction: The Social Networks Perspective, Historical and Theoretical Foundations,
Fundamental Concepts in Network Analysis, Distinctive Features.
Social Network Data: What are Network Data? Boundary Specification and Sampling, Types
of Networks, Network Data, Measurement and Collection.
Graph Theory and Social Networks: Graphs: Basic Definitions, Paths and Connectivity,
Distance and Breadth-First Search.
UNIT – 2 8 Hrs
Strong and Weak Ties: Triadic Closure, The Strength of Weak Ties, Tie Strength and Network
Structure in Large-Scale Data, Tie Strength, Social Media, and Passive Engagement, Closure,
Structural Holes, and Social Capital.
Networks in Their Surrounding Contexts: Homophily, Mechanisms Underlying Homophily:
Selection and Social Influence, Affiliation.
Positive and Negative Relationships: Structural Balance, Characterizing the Structure of
Balanced Networks.
UNIT – 3 6 Hrs
Information Networks and the World Wide Web: The Structure of the web: The World
Wide Web, Information Networks, Hypertext, and Associative Memory, The Web as a
Directed Graph, The Bow-Tie Structure of the Web.
Link Analysis and Web Search: Searching the Web: The Problem of Ranking, Link Analysis
using Hubs and Authorities, PageRank.
UNIT – 4 8 Hrs
Network Dynamics: Information Cascades, Following the Crowd, A Simple Herding
Experiment , Bayes’ Rule: A Model of Decision-Making Under Uncertainty , Bayes’ Rule in the
Herding Experiment , A Simple, General Cascade Model , Sequential Decision-Making and
Cascades.
Structural Models: Cascading Behavior in Networks: Diffusion in Networks, Modeling
Diffusion through a Network, Cascades and Clusters, Diffusion, Thresholds, and the Role of
Weak Ties.
UNIT – 5 6 Hrs
The Small-World Phenomenon: Six Degrees of Separation, Structure and Randomness,
Decentralized Search, Modeling the Process of Decentralized Search, Core-Periphery
Structures and Difficulties in Decentralized Search.
Text Books:
1. Social Network Analysis: Methods and Applications, Stanley Wasserman, Katherine
Faust, Cambridge University Press, 2012 (Unit 1)
2. Networks, Crowds, and Markets: Reasoning about a Highly Connected World : David
Easley, Jon Kleinberg.
 Reference Books:
1. Social Network Analysis by John Scott, 3rd edition, SAGE publications Ltd, 2012.

2. Understanding-Social-Networks-Theories-Concepts-and findings by Charles

Kadushin, Oxford university press, 2012.

Course Outcomes

CO1 Evaluating social network analysis in empirical research and map the steps of replication

CO2 Analyse data connectivity problems by using social network algorithms.

CO3 Visualize, Measure and Compare social network problems.

CO – PO - PSO Mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 3 2
CO2 2 2
CO3 3 2 2 2

Massive Open Online Course (MOOC)

Sl.
No Course Offered by Course Link
.
1. [Link]
Social Networks NPTEL
2.
Social Network [Link]
Coursera
Analysis
3. Social Network [Link]
NPTEL
Analysis
4. [Link]
Starting with Social
Udemy S4SALEA
Network Analysis

Semester End Examination (SEE) Question Paper Pattern:

Internal Choice /
UNIT # Unit Wise Marks Distribution
Mandatory
Unit 1 Mandatory One question to be asked for 20 marks

Unit 2 Internal Choice Two questions to be asked for 20 marks each

Unit 3 Mandatory One question to be asked for 20 marks

Unit 4 Internal Choice Two questions to be asked for 20 marks each

Unit 5 Mandatory One question to be asked for 20 marks

Percentage of Questions to be included in SEE

Bloom’s Level
Question Paper
Remember / Understand 25%

Apply / Analyze 50%

Create / Evaluate 25%

Assessment Pattern:
Category Score Split up Total
CIE - 1 20M
CIE – 2 (Best of Two)
Theory 25M
CIE - 3
Continuous Internal AAT/Quiz 05M
Evaluation (CIE)
CIE - 1 10M
Lab CIE – 2 10M 25M
AAT 05M
Semester End
100M (50% weightage) 50M
Examination (SEE)
Total 100M
 Course Title CYBER PHYSICAL SYSTEMS
Course Code 24AM7PECYS Credits 3 L-T-P 3-0-0
CIE 50 Marks SEE 100 Marks (50% Weightage)
Contact Hours / Week 3 Total Lecture Hours 36

UNIT – 1 7 Hrs
Evolution of Cyber-Physical Systems: Overview, The Need for a Transdisciplinary
Approach, Key Features of Cyber-Physical Systems, Challenges, and Applications,
Synchronous Model: Reactive Components, Properties of Components, Composing
Components, Synchronous Designs.
UNIT – 2 7 Hrs
Asynchronous Model: Asynchronous Processes, Asynchronous Design Primitives,
Asynchronous Coordination Protocols.
Timed Models: Timed Processes, Timing-Based Protocols, Timed Automata, Timed
Models of Computation.
UNIT – 3 8 Hrs
Cyber-Physical Systems Built on Wireless Sensor Networks: System Description and
Operational Scenarios, Medium Access Control, Routing, Node Localization, Clock
Synchronization, Power Management, Key Design Drivers and Quality Attributes
Principles of Dynamical Systems: Continuous-Time Models, Linear Systems, Designing
Controllers, Analysis Techniques.
UNIT – 4 8 Hrs
Hybrid Systems: Modal Models, Classes of Hybrid Systems, Hybrid Dynamical Models,
Designing Hybrid Systems, Linear Hybrid Automata.
Security of Cyber-Physical Systems: Basic Techniques, Cyber Security Requirements,
Attack Model, Countermeasures, Advanced Techniques.
UNIT – 5 6 Hrs
Cyber-Physical System Application Domains: Medical Cyber-Physical Systems, System
Description and Operational Scenarios, Key Design Drivers and Quality Attributes, On-
Demand Medical Devices and Assured Safety
Text Books:
1. E. A. Lee and S. A. Seshia, Introduction to Embedded Systems - A Cyber-Physical
Systems Approach, Second Edition, MIT Press, 2017.
2. Suh, Sang C., U. John Tanik, John N. Carbone, and Abdullah Eroglu, eds. Applied
cyber-physical systems. Springer New York, 2014.
3. R. Rajkumar, D. de. Niz and M. Klein, (2017), Cyber Physical Systems, Addison-Wesle
Reference Books:
1. R. Alur, “Principles of Cyber-Physical Systems,” MIT Press, 2015.
2. Andre Platzer, Logical Foundations of Cyber-Physical Systems, (2e), Springer
Publishing, 2018.
3. C. Cassandras, S. Lafortune, “Introduction to Discrete Event Systems”, Springer
2007.
 Course Outcomes
CO1 Apply the architectural design principles of Cyber physical System (CPS).
CO2 Design CPS using synchronous, asynchronous and timed models.
CO3 Analyze various modeling, safety and security techniques of CPS

CO – PO - PSO Mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 3 3
CO2 3 3
CO3 3 3

Massive Open Online Course (MOOC)

Sl.
Course Offered by Course Link
No.
1. Foundations of Cyber
Physical Systems NPTEL [Link]

2. Cyber-Physical
[Link]
Systems: Modeling Coursera
systems-1
and Simulation

Semester End Examination (SEE) Question Paper Pattern:

Internal Choice /
UNIT # Unit Wise Marks Distribution
Mandatory
Unit 1 Mandatory One question to be asked for 20 marks

Unit 2 Mandatory One question to be asked for 20 marks

Unit 3 Internal Choice Two questions to be asked for 20 marks each

Unit 4 Internal Choice Two questions to be asked for 20 marks each

Unit 5 Mandatory One question to be asked for 20 marks

Percentage of Questions to be included in SEE

Bloom’s Level
Question Paper
Remember / Understand 35%

Apply / Analyze 40%

Create / Evaluate 25%

Assessment Pattern:
Category Score Split up Total
CIE - 1 40M
Continuous Internal CIE – 2 (Best of Two)
Theory 50M
Evaluation (CIE) CIE - 3
AAT/Quiz 10M
Semester End
100M (50% weightage) 50M
Examination (SEE)
Total 100M
 Course Title INTRODUCTION TO ARTIFICIAL INTELLIGENCE
Course Code 24AM7OEAIG Credits 3 L-T-P 3-0-0
CIE 50 Marks SEE 100 Marks (50% Weightage)
Contact Hours /Week 3 Total Lecture Hours 36

UNIT – 1 7 Hrs
Introduction: What is AI? Intelligent Agents: How agent should act, Structure
of Intelligent Agents, Environments Problem Solving: Formulating problems,
Example problems Uniformed-search strategies: Breadth-First Search,
Uniform Cost Search, Depth-First Search, Depth Limited Search, Iterative
Deepening Search.
UNIT – 2 7 Hrs
Heuristic Search Strategies: Generate-and-Test, Hill Climbing, Best-first
Search, Problem Reduction, Constraint Satisfaction, Means-ends Analysis.
UNIT – 3 7 Hrs
Knowledge Representation: Propositional Logic – Syntax and Semantics,
Using Propositional Logic, First-Order Logic – Syntax and Semantics, Using
First-Order Logic Representing Knowledge using Rules: Procedural Versus
Declarative Knowledge, Forward Versus Backward Reasoning, Semantic
Knowledge, Ontology Based representation.
UNIT – 4 8 Hrs
Uncertain Knowledge & Reasoning: Acting under Uncertainty, The Wumpus
World Revisited, Representing Knowledge in an Uncertain Domain, The
Semantics of Belief Networks, Efficient Representation of Conditional
Distributions, Exact Inference in Bayesian Networks, Approximate Inference in
Bayesian Networks, Relational and First-Order Probability Models, Other
Approaches to Uncertain Reasoning.
UNIT – 5 7 Hrs
Introduction to Expert Systems: Definition, Features of an Expert System,
Organization, Characteristics, Prospector, Knowledge Representation in Expert
Systems, Expert System tools – MYCIN, EMYCIN.
Text Books:
1. Artificial Intelligence - A Modern Approach, Stuart Russell and Peter
Norvig, 3rd Edition, Pearson, 2014.
Reference Books:
1. Artificial Intelligence, Elaine Rich, Kevin Knight and Shivashankar B Nair,
3rd Edition, McGraw-Hill Education, 2015.
2. Introduction to Artificial Intelligence and Expert Systems, Dan W
Patterson, Pearson, 2015.

Course Outcomes
Apply the principles of Intelligent Agents to address problem-solving challenges through
CO1
search strategies.
Construct procedural and declarative knowledge through the implementation of agent-
CO2
based rules, facilitating a logic-based analysis.
Assess the probabilities associated with managing uncertain knowledge and utilize the
CO3
principles of expert systems effectively.

CO – PO - PSO Mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 2 2
CO2 3 2
CO3 1 1 2
Massive Open Online Course (MOOC)
Sl.
Course Offered by Course Link
No.
1. Introduction to
NPTEL [Link]
Artificial Intelligence
2.
Introduction to
Coursera [Link]
Artificial Intelligence
3. Artificial Intelligence :
Knowledge
NPTEL [Link]
Representation and
Reasoning

Semester End Examination (SEE) Question Paper Pattern:

Internal Choice /
UNIT # Unit Wise Marks Distribution
Mandatory
Unit 1 Mandatory One question to be asked for 20 marks

Unit 2 Internal Choice Two questions to be asked for 20 marks each

Unit 3 Internal Choice Two questions to be asked for 20 marks each

Unit 4 Mandatory One question to be asked for 20 marks

Unit 5 Mandatory One question to be asked for 20 marks

Percentage of Questions to be included in SEE

Bloom’s Level
Question Paper
Remember / Understand 25%

Apply / Analyze 50%

Create / Evaluate 25%

Assessment Pattern:
Category Score Split up Total
CIE - 1 40M
Continuous Internal CIE – 2 (Best of Two)
Theory 50M
Evaluation (CIE) CIE - 3
AAT/Quiz 01M
Semester End
100M (50% weightage) 50M
Examination (SEE)
Total 100M
 Course Title INTRODUCTION TO MACHINE LEARNING
Course Code 24AM7OEMLG Credits 3 L-T-P 3-0-0
CIE 50 Marks SEE 100 Marks (50% Weightage)
Contact Hours/Week 3 Total Lecture Hours 36

UNIT - 1 7 Hours
Introduction: Types, Applications and Challenges of Machine Learning, Testing and Validating,
Learning problems, Designing a Learning system, Perspectives and Issues.
UNIT - 2 6 Hours
Concept Learning Task: Concept learning task as search, Find-S algorithm, Version space,
Candidate Elimination algorithm.
UNIT - 3 8 Hours
Supervised Learning: Instance Based Learning, Support Vector Machines: Linear and Non-
Linear, k- Nearest Neighbor [Link] Models-linear and logistic regression
UNIT - 4 7 Hours
Decision Tree Learning: Decision tree representation, Problems, ID3 algorithm, Pruning, Rule
extraction from Decision trees.
UNIT - 5 8 Hours
Unsupervised Learning: Types and Challenges, Clustering – K means, DBSCAN, Hierarchical,
Association Rule Mining, Anomaly detection. Reinforcement Learning: Introduction, The
learning task.
Text Books:
1. Machine Learning, Tom Mitchell, McGraw Hill, 3rd Edition, 1997.
2. Introduction to Machine Learning, Ethem Alpaydın, 3rd Edition, MIT press, 2014.
Reference Books:
1. MACHINE LEARNING - An Algorithmic Perspective, Stephen Marsland, 2nd Edition, 2015.
2. Introduction to Machine Learning with Python, A Guide for Data Scientists, Andreas
[Link] and Sarah Guido, O’Reilly Media, 2017.
3. Hands-on Machine Learning with Scikit-Learn and Tensor Flow: concepts, tools, and
techniques to build intelligent systems, Aurelien Geron, O'Reilly Media, 2019.

Course Outcomes
CO1 Apply the concepts of Machine Learning techniques to solve the problems across various
domains.
CO2 Analyze the given data for modeling and prediction using machine learning techniques.
CO3 Provide solutions for real time applications using Machine Learning techniques.

CO-PO-PSO Mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 3 2
CO2 2 2
CO3 1 2 2 2 2
Massive Open Online Course (MOOC)
Sl.
Course Offered by Course Link
No.
Machine Learning –
[Link]
1 Introduction to Coursera
introduction-for-everyone
everyone
Introduction to Machine [Link]
2 NPTEL
Learning 9/

Semester End Examination (SEE) Question Paper Pattern:

UNIT Internal Choice/
Unit Wise Marks Distribution
# Mandatory
Unit
Mandatory One question to be asked for 20 marks each
1
Unit
Mandatory One question to be asked for 20 marks each
2
Unit
Internal Choice Two questions to be asked for 20 marks each
3
Unit
Mandatory One question to be asked for 20 marks each
4
Unit
Internal Choice Two questions to be asked for 20 marks each
5

Percentage of Questions to be included in SEE

Bloom’s Level
Question Paper
Remember /
20%
Understand
Apply / Analyze 70%

Create / Evaluate 10%

Assessment Pattern
Category Score Split up Total
CIE –
1
CIE – 40 M
2 (Best of Two)
Continuous Internal CIE –
Theory 3 50M
Assessment (CIE)
Quiz 05M

AAT 05M

Semester End Examination

100M (50% weightage) 50M
(SEE)
Total 100M
Course Title INTRODUCTION TO NEURAL NETWORKS
Course Code 24AM7OEINN Credits 3 L-T-P 3-0-0
CIE 50 Marks SEE 100 Marks (50% Weightage)
Contact Hours /Week 3 Total Lecture Hours 36

UNIT – 1 7Hrs
Introduction: What is a Neural Network? , Models of a Neuron , Neural
Networks Viewed As Directed Graphs, Feedback, Network Architectures,
Knowledge Representation. Rosenblatt’s Perceptron: Introduction,
Perceptron , The Perceptron Convergence Theorem , Relation Between the
Perceptron and Bayes Classifier for a Gaussian ,The Batch Perceptron
Algorithm, Filtering structure of the LMS Algorithm, Unconstrained
Optimization: a Review.
UNIT – 2 8Hrs
Multilayer Perceptron’s-1 : Introduction , Some Preliminaries , Batch Learning
and On-Line Learning, The Back-Propagation Algorithm , XOR Problem ,
Heuristics for Making the Back-Propagation Algorithm Perform Better, Back
Propagation and Differentiation, The Hessian and Its Role in On-Line Learning,
Optimal Annealing and Adaptive Control of the Learning Rate.
UNIT – 3 7 Hrs
Multilayer Perceptron’s-2 :Generalization Approximations of Functions,
Cross-Validation, Complexity Regularization and Network Pruning, Virtues and
Limitations of Back-Propagation Learning, Supervised Learning Viewed as an
Optimization Problem.
UNIT – 4 7 Hrs
Radial-Basis Function Networks: Introduction , Cover’s Theorem on the
Separability of Patterns , The Interpolation Problem , Radial-Basis-Function
Networks, Recursive Least-Squares Estimation of the Weight Vector, Hybrid
Learning Procedure for RBF Networks.
UNIT – 5 7Hrs
Self-Organizing Maps : Introduction ,Two Basic Feature-Mapping Models , Self-
Organizing Map , Properties of the Feature Map, Contextual Maps ,Hierarchical
Vector Quantization, Kernel Self-Organizing Map, Relationship Between Kernel
SOM and Kullback–Leibler Divergence.
Text Books:
1. Neural Networks and Learning Machines, Simon Haykin, PHI, 3rd Edition,
2016.
Reference Books:
1. Neural Networks a Comprehensive Foundations, Simon Haykin, PHI, 2nd
Edition.
2. Neural Networks - A Classroom Approach, Sathish Kumar, McGraw Hill
Education 2nd Edition.
3. Introduction to Artificial Neural Systems, Jacek M. Zurada, JAICO
Publishing House Ed. 2006.

Course Outcomes
 Apply the basic principles of neural networks to build and train neural networks models using
CO1
various frameworks.
Assess and Enhance Model Effectiveness through Metric Analysis and Performance Optimization
CO2
Techniques.
Demonstrate the practical implementation of neural networks in addressing real-world
CO3
challenges across diverse domains.
CO – PO - PSO Mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3

CO1 1 2

CO2 2 2

CO3 2 1 2

Massive Open Online Course (MOOC)

Sl.
Course Offered by Course Link
No.
1. Neural Networks
NPTEL [Link]
and Applications
2. Neural Networks [Link]
Coursera
and Deep Learning learning
3. Neural Networks
for Signal NPTEL [Link]
Processing - I

Semester End Examination (SEE) Question Paper Pattern:

Internal Choice /
UNIT # Unit Wise Marks Distribution
Mandatory
Unit 1 Internal Choice Two questions to be asked for 20 marks each

Unit 2 Mandatory One question to be asked for 20 marks

Unit 3 Internal Choice Two questions to be asked for 20 marks each

Unit 4 Mandatory One question to be asked for 20 marks

Unit 5 Mandatory One question to be asked for 20 marks

Percentage of Questions to be included in SEE

Bloom’s Level
Question Paper
Remember / Understand 25%

Apply / Analyze 50%

Create / Evaluate 25%

Assessment Pattern:
Category Score Split up Total
CIE - 1
40M
CIE – 2 (Best of Two)
Continuous Internal Theory 50M
CIE - 3
Evaluation (CIE)
AAT 05M
Quiz 05M
 Semester End
100M (50% weightage) 50M
Examination (SEE)
Total 100M
Course Title PROJECT WORK-2
24AM7PWPW
Course Code Credits 5 L-T-P 0-0-5
2
CIE 50 Marks SEE 100 Marks (50% Weightage)
Contact Hours / Week 10 Total Lecture Hours --

Project work-2: The student will continue the identified engineering problem and design
solutions carried out during Project work-1. A detailed implementation, Modules Integration
and Testing has to be carried out. Students also have to prepare a detailed project report.
The outcome of the capstone project should be either published in a reputed
conference/journal of Scopus/Web of science indexed, based on the strength of the work
carried out. If the outcome of the project is a combination of software and hardware it is
recommended to apply for patent. The students should be encouraged to submit their work in
project competitions/Ideathon either national or international forums, government agencies
like KSCST, VGST, etc.

Rules and Regulations

• The student shall submit the progress report every week showing the progress made, to
their respective guides.
• The project report shall be submitted as per the approved guidelines and formats.
• Marks are awarded to each student of the project group based on the individual
performance in the viva-voce external examination.
• If a candidate fails to submit the project report on or before the specified
deadline, he/she is deemed to have failed in the Project Work and shall re-register for the
same in a subsequent semester.

Review-1: Shall be reviewed by the panel consisting of three internal faculty. At the
time of Project Work Review 1, the students should be able to satisfy the below
outcomes:
Sl. No. Parameters Marks
1 Methodology and Implementation 10
2 Individual contribution, team work and 10
communication.

Review-2: Shall be reviewed by the panel consisting of three internal faculty members.
At the time of Project Work Review 2, the students should be able to satisfy the below
outcomes:
Sl. No. Parameters Marks
1 Testing and Results 10
2 Ethical Considerations, Societal impact, 10
innovation and creativity
3 Project Report 10
 COURSE OUTCOMES (COs)
At the end of the course, the student will be able to:
CO 1: Demonstrate proficiency in the technical skills and tools applied in their project.
CO 2: Apply project management principles to organize and manage their project
effectively.
CO 3: Function effectively within the team and contribute to its success while adhering
to standards, legal requirements, and ethical practices.

CO – PO - PSO Mapping
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
CO1 3 1
CO2 2 1
CO3 1 1 1 1 1

Assessment Pattern:
Category Score Split up Total
Continuous Internal Review 1 20M
50M
Evaluation (CIE) Review 2 30M
Semester End
100M (50% weightage) 50M
Examination (SEE)
Total 100M