SEMESTER – I Hours/week: 4

PDS1501 Credits :4

INTRODUCTION TO DATA SCIENCE

.
Unit – I: Introduction
Introduction to Data Science – Evolution of Data Science – Data Science Roles – Stages in a
Data Science Project – Applications of Data Science in various fields – Data Security Issues.

Unit – II: Data Collection and Data Pre-Processing

Data Collection Strategies – Data Pre-Processing Overview – Data Cleaning – Data
Integration and Transformation – Data Reduction – Data Discretization.

Unit – III: Exploratory Data Analytics

Descriptive Statistics – Mean, Standard Deviation, Skewness and Kurtosis – Box Plots –
Pivot Table – Heat Map – Correlation Statistics – ANOVA.

Unit – IV: Model Development

Simple and Multiple Regression – Model Evaluation using Visualization – Residual Plot –
Distribution Plot – Polynomial Regression and Pipelines – Measures for In-sample
Evaluation – Prediction and Decision Making.

Unit – V: Model Evaluation

Generalization Error – Out-of-Sample Evaluation Metrics – Cross Validation – Overfitting –
Under Fitting and Model Selection – Prediction by using Ridge Regression – Testing
Multiple Parameters by using Grid Search.

REFERENCES:

1. Jojo Moolayil, “Smarter Decisions : The Intersection of IoT and Data Science”,
PACKT, 2016.
2. Cathy O’Neil and Rachel Schutt , “Doing Data Science”, O'Reilly, 2015.
3. David Dietrich, Barry Heller, Beibei Yang, “Data Science and Big data Analytics”,
EMC 2013
4. Raj, Pethuru, “Handbook of Research on Cloud Infrastructures for Big Data
Analytics”, IGI Global.
SEMESTER – I Hours/week: 4
PDS1502 Credits :4

STATISTICS FOR DATA SCIENCE

.
Unit – I: Descriptive Statistics
Sampling Techniques – Data Classification – Tabulation – Frequency and graphic
Representation – Measures of Central Tendency – Measures of Variation – Quartiles and
Percentiles – Moments - Skewness and Kurtosis.

Unit – II: Correlation and Regression

Scatter Diagram – Karl Pearson’s Correlation Coefficient – Rank Correlation - Correlation
Coefficient for Bivariate Frequency Distribution – Regression Coefficients – Fitting of
Regression Lines.

Unit – III: Probability Theory

Random Experiment – Sample Space – Events – Axiomatic Definition of Probability –
Addition Theorem – Multiplication Theorem – Baye’s Theorem -Applications.

Unit – IV: Distribution Function

Continuous and Discrete Random Variables – Distribution Function of a Random Variable –
Probability Mass Functions and Probability Density Functions – Characteristic Functions –
Central Limit Theorems.

Unit – V: Probability Distributions

Probability Distributions – Recurrence Relationships – Moment Generating Functions –
Cumulant Generating Functions – Continuous Probability Distributions - Rectangular
Distribution – Binomial Distribution – Poisson Distribution – Continuous Probability
Distributions – Uniform Distribution - Normal Distribution – Exponential Distribution.

REFERENCES:
1. Gupta, S.C. and Kapoor, V.K.: “Fundamentals of Mathematical Statistics”, Sultan &
Chand & Sons, New Delhi, 11th Ed, 2002.
2. Hastie, Trevor, et al. “The elements of Statistical Learning”, Springer, 2009.
3. Practical Statistics for Data Scientists, 2nd Edition, Peter Bruce, Andrew Bruce and
Peter Gedeck, May 2020
4. Statistics for Machine Learning, By Pratap Dangeti, July 2017
SEMESTER – I Hours/week: 5
PDS1503 Credits :5
PYTHON FOR DATA SCIENCE
.
Unit – I: Data Structures and OOP
Python Program Execution Procedure – Statements – Expressions – Flow of Controls –
Functions – Numeric Data Types – Sequences – Strings – Tuples – Lists – Dictionaries.

Class – Constructors – Object Creation – Inheritance – Overloading.

Text Files and Binary Files – Reading and Writing.

Unit – II: Numpy and Pandas Packages

NumPy ndarray - Vectorization Operation - Array Indexing and Slicing - Transposing Array
and Swapping Axes - Saving and Loading Array - Universal Functions - Mathematical and
Statistical Functions in Numpy .

Series and DataFrame data structures in pandas - Creation of Data Frames – Accessing the
columns in a DataFrame - Accessing the rows in a DataFrame - Panda’s Index Objects -
Reindexing Series and DataFrames - Dropping entries from Series and Data Frames -
Indexing, Selection and Filtering in Series and Data Frames - Arithmetic Operations between
Data Frames and Series - Function Application and Mapping.

Unit – III: Data Wrangling

Combining and Merging Data Sets – Reshaping and Pivoting – Data Transformation – String
manipulations – Regular Expressions.

Unit – IV: Data Aggregation and Group Operations

GroupBy Mechanics – Data Aggregation – GroupWise Operations – Transformations – Pivot
Tables – Cross Tabulations – Date and Time data types.

Unit – V: Visualization in Python

Matplotlib and Seaborn Packages – Plotting Graph - Controlling Graphs – Adding Text –
More Graph Types – Getting and Setting Values – Patches.

REFERENCES:
1. Gowrishanker and Veena, “Introduction to Python Programming”, CRC Press,
2019.
2. Python Crash Course, 2nd Edition, By Eric Matthes, May 2019
3. NumPy Essentials, By Leo Chin and Tanmay Dutta, April 2016
4. Joel Grus, “Data Science from scratch”, O'Reilly, 2015.
5. Wes Mc Kinney, “Python for Data Analysis”, O'Reilly Media, 2012.
6. Kenneth A. Lambert, (2011), “The Fundamentals of Python: First Programs”,
Cengage Learning
7. Jake Vanderplas. Python Data Science Handbook: Essential Tools for
Working with Data 1st Edition.
SEMESTER – I Hours/week: 4
PDS1504 Credits :4

PYTHON FOR DATA SCIENCE - LAB

LIST OF EXERCISES:
1. Editing and executing Programs involving Flow Controls.
2. Editing and executing Programs involving Functions.
3. Program in String Manipulations
4. Creating and manipulating a Tuple
5. Creating and manipulating a List
6. Creating and manipulating a Dictionary
7. Object Creation and Usage
8. Program involving Inheritance
9. Program involving Overloading
10. Reading and Writing with Text Files and Binary Files
11. Combining and Merging Data Sets
12. Program involving Regular Expressions
13. Data Aggregation and GroupWise Operations
SEMESTER – I Hours/week: 4
PDS1505 Credits :4

RDBMS LAB

1. Creating a database
2. Creating a table
3. Inserting records in a table
4. Altering the table structure.
5. Deleting data from table
6. Updating data from table.
7. Select command
8. Where clause
9. Aggregate functions
10. Numeric functions ( Absolute, ceiling, floor, modulo, round off, square, Square Root,
power)
11. Constraints
12. Group By, Having
13. Operators (and, or, not between, In , not in, is null, is not null, like, Order By)
14. String Functions (Lower, Upper, Replace, left-trim, right-trim, substring, Length,
rename)
15. Drop (table, database)
16. Truncate
17. Sub Queries, Alias
SEMESTER – I Hours/week: 5
PDS1506 Credits :5

MACHINE LEARNING
.
Unit – I: Introduction
Machine Learning Foundations – Overview – Design of a Learning System – Types of
Machine Learning – Supervised Learning and Unsupervised Learning – Mathematical
Foundations of Machine Learning – Applications of Machine Learning.

Unit – II: Supervised Learning - I

Simple Linear Regression – Multiple Linear Regression – Polynomial Regression – Ridge
Regression – Lasso Regression – Evaluating Regression Models – Model Selection –
Bagging – Ensemble Methods.

Unit – III: Supervised Learning - II

Classification – Logistic Regression – Decision Tree Regression and Classification –
Random Forest Regression and Classification – Support Vector Machine Regression and
Classification - Evaluating Classification Models.

Unit – IV: Unsupervised Learning

Clustering – K-Means Clustering – Density-Based Clustering – Dimensionality Reduction –
Collaborative Filtering.

Unit – V: Association Rule Learning and Reinforcement Learning

Association Rule Learning – Apriori – Eclat – Reinforcement Learning – Upper Confidence
Bound – Thompson Sampling – Q-Learning.

REFERENCES:

1. Kevin P. Murphy, “Machine Learning: A Probabilistic Perspective”, MIT

Press, 2012.
2. Ethem Alpaydin, “Introduction to Machine Learning”, MIT Press, Third
Edition, 2014.
3. Tom Mitchell, "Machine Learning", McGraw-Hill, 1997.
4. Sebastian Raschka, Vahid Mirjilili,”Python Machine Learning and deep learning”, 2nd
edition, kindle book, 2018
5. Carol Quadros,”Machine Learning with python, scikit-learn and Tensorflow”, Packet
Publishing, 2018
6. Gavin Hackeling,” Machine Learning with scikit-learn”, Packet publishing, O’Reily,
2018
7. Stanford Lectures of Prof. Andrew Ng on Machine Learning
SEMESTER – I Hours/week: 4
PDS1507 Credits :4

MACHINE LEARNING - LAB

.

1. Write a program to implement the naïve Bayesian classifier for a sample training data set
stored as a .CSV file. Compute the accuracy of the classifier, considering few test data sets.

2. Assuming a set of documents that need to be classified, use the naïve Bayesian algorithm.

3. Classifier model to perform this task. Built-in Java classes/API can be used to write the
program. Calculate the accuracy, precision, and recall for your data set.

4. Write a program to implement k-Nearest Neighbour algorithm to classify the iris. print
both correct and wrong predictions. Java/Python ML library classes can be used for this
problem.

5. Write a program to implement Logistic Regression algorithm to classify the housing price
data set. Print both correct and wrong predictions. Java/Python ML library classes can be
used for this problem.

6. Write a program to implement and compare SVM, KNN and Logistic regression algorithm
to classify the iPhone purchase records data set. Print both correct and wrong predictions.
Java/ Python ML library classes can be used for this problem.
SEMESTER – II Hours/week: 4

PDS2501 Credits :4
STATISTICAL INFERENCE

UNIT – I: TESTING OF HYPOTHESIS - PART 1

Testing of Hypothesis - Statistical Hypothesis - Simple and composite hypothesis, Null and
Alternative hypothesis - two kinds of errors, level of significance, size and power of a test,
most powerful test, Neyman-Pearson lemma with proof.

UNIT – II: TEST OF HYPOTHESIS – PART 2

Simple examples using Neyman-Pearson lemma .Uniformly most powerful tests and
unbiased tests based on normal Likelihood ratio test (without proof) and its properties.
Application of LR test for single mean.

UNIT – III: TEST OF SIGNIFICANCE FOR LARGE SAMPLES

Test of significance for mean(s), variance(s), proportion(s), correlation coefficient(s) based
on Normal distribution.

UNIT – IV: TEST OF SIGNIFICANCE FOR SMALL SAMPLES

Test of significance for mean(s), variance(s), correlation coefficient(s), regression coefficient,
based on t, Chi-square and F-distributions. Applications of Chi-square in test of significance
(independence of attributes, goodness of fit).

UNIT – V:
Non-parametric tests – Kolmogorov -Smirnov test, Sign test, Wald- Wolfowitz run test, run
test for randomness, median test, Wilcoxon test and Wilcoxon – Mann-Whitney U test.

REFERENCE BOOKS

1. Gupta, S.C. and Kapoor, V.K.: “Fundamentals of Mathematical Statistics”, Sultan &
Chand & Sons, New Delhi, 11th Ed, 2002.
2. Rohatgi, V.K. : “Statistical Inference”, John Wiley and sons, 1984.
3. Hogg, R.V, Craig. A.T. and Tannis: “Introduction to mathematical statistics”, Prentice
Hall, England, 1995.
4. Dudewicz. E.J and Mishra.S.N.: “Modern Mathematical statistics”, John Wiley and sons,
1988.
SEMESTER – II Hours/week: 4
PDS2502 Credits :4

BIG DATA ANALYTICS THROUGH SPARK

.
Unit – I: Introduction to Spark
Apache Spark Ecosystem - Setting up the Spark Python Environment – Execution of a
PySpark Program – Resilient Distributed Datasets – Spark Architecture – Spark Project
Workflow.

Unit – II: Spark Programming with Python

Loading and Storing Data – Transformations – Actions – Key-Value Resilient Distributed
Datasets – Local Variables – Broadcast Variables – Accumulators – Partitioning –
Persistence.

Unit – III: Spark SQL

Overview of Spark SQL – Spark Session – Data Frames – Schema of a Data Frame –
Operations supported by Data Frames – Filter, Join, GroupBy, Agg operations – Nesting the
Operations – Temporary Tables – Viewing and Querying Temporary Tables.

Unit – IV: Spark Streaming

Use Cases for Realtime Analytics – Transferring, Summarizing, Analysing Realtime data –
Data Sources supported by Spark Streaming – Flat files, TCP/IP – Flume – Kafka – Kinesis –
Streaming Context – DStreams – Dstream RDDs – Dstream Processing.

Unit – V: Machine Learning with Spark

Linear Regression – Decision Tree Classification – Principal Component Analysis – Random
Forest Classification – Text Pre-processing with TF-IDF – Naïve Bayes Classification – K-
Means Clustering – Recommendation Engines.

REFERENCES:
1. Tomasz Drabos, “Learning PySpark”, PACKT, 2017.
2. Padma Priya Chitturi, “Apache Spark for Data Science”, PACKT, 2017.
3. Holden Karau, “ Learning Spark”. PACKT, 2016.
4. Sandy Riza, “Advanced Analytics with Spark”, O’ Reilly, 2016.
5. Romeo Kienzler, “Mastering Apache Spark”, PACKT, 2017.
SEMESTER – II Hours/week: 4
PDS2503 Credits :4

BIG DATA ANALYTICS THROUGH SPARK - LAB

LIST OF EXERCISES:
1. Program involving Resilient Distributed Datasets
2. Program involving Transformations and Actions
3. Program involving Key-Value Resilient Distributed Datasets
4. Program involving Local Variables, Broadcast Variables and Accumulators
5. Program involving Filter, Join, GroupBy, Agg operations
6. Viewing and Querying Temporary Tables
7. Transferring, Summarizing and Analysing Twitter data
8. Program involving Flume, Kafka and Kinesis
9. Program involving DStreams and Dstream RDDs
10. Linear Regression
11. Decision Tree Classification
12. Principal Component Analysis
13. Random Forest Classification
14. Text Pre-processing with TF-IDF
15. Naïve Bayes Classification
16. K-Means Clustering
SEMESTER – II Hours/week: 4
PDS2504 Credits :4

NOSQL DATABASES

 An Overview of NoSQL (1 hour)

 HDFS (3 hours)
 Apache Hive as an HDFS Data Warehouse (5 hours)
 HBase (5 hours)
 MongoDB (6 hours)
 Cassandra (7 hours)
 Neo4j (3 hours)

Unit – I: NoSQL and HDFS

Unit – II: Hive

Unit – III: HBase

Unit – IV: MongoDB

Introduction – Features - Data types - Mongo DB Query language - CRUD operations – Arrays
- Functions: Count – Sort – Limit – Skip – Aggregate - Map Reduce. Cursors – Indexes -
Mongo Import – Mongo Export.

Unit – V: Cassendra
Introduction – Features - Data types – CQLSH - Key spaces - CRUD operations – Collections –
Counter – TTL - Alter commands - Import and Export - Querying System tables.
SEMESTER – II Hours/week: 4
PDS2505 Credits :4

NOSQL DATABASES - LAB

 Exercises on HDFS
 Exercises on Apache Hive as an HDFS Data Warehouse
 Exercises on HBase
 Exercises on MongoDB
 Exercises on Cassandra
 Exercises on Neo4j
SEMESTER – II Hours/week: 4
PDS2601 Credits :3

ELECTIVE 1A: FINANCIAL ANALYTICS

Unit: I
Introduction: Meaning-Importance of Financial Analytics uses-Features-Documents used in
Financial Analytics: Balance Sheet, Income Statement, Cash flow statement-Elements of
Financial Health: Liquidity, Leverage, Profitability. Financial Securities : Bond and Stock
investments - Housing and Euro crisis - Securities Datasets and Visualization - Plotting
multiple series.
Unit: II
Using Excel to Summarize Data, Slicing and Dicing Financial Data with PivotTables, Excel
Charts to Summarize Marketing Data. Excel Functions to Summarize Data, Pricing
Analytics, Risk based pricing, Fraud Detection and Prediction, Recovery Management, Loss
Risk Forecasting, Risk Profiling, Portfolio Stress Testing.
Unit: III
Descriptive Analytics, Data Exploration, Dimension Reduction and Data Clustering
Geographical Mapping Market Basket Analysis. Predictive Analytics Fraud Detection Churn
Analysis Crime Mapping, Content Analytics Sentiment Analysis
Unit: IV
Forecasting Analytics Estimating Demand Curves and Optimize Price, Price Bundling, Non
Linear Pricing and Price Skimming, Forecasting, Simple Regression and Correlation Multiple
Regression to forecast sales. Modelling Trend and Seasonality Ratio to Moving Average
Method, Winter’s Method
UNIT - V
Analyzing financial data and implement financial models using R. Process of Data analytics
using R: obtaining publicly available data, refining such data, implement the models and
generate typical output, Prices and individual security returns, Portfolio returns, Risks, Factor
Models
TEXTBOOKS

 Analysis of Economic Data, Gary Koop, (4th Edition), Wiley.

 Statistics and Data Analysis for Financial Engineering: with R examples;
David Ruppert, David S. Matteson, Springers.

REFERENCE BOOKS

 Analyzing Financial Data and Implementing Financial Models Using ‘R’, Ang
Clifford, Springers.
 Microsoft Excel 2013: Data Analysis and Business Modeling, Wayne L.
Winston, Microsoft Publishing
SEMESTER – II Hours/week: 4
PDS2602 Credits :3

ELECTIVE 1B: HEALTH ANALYTICS

UNIT I
Introduction
Introduction to Healthcare Data Analytics- Electronic Health Records– Components of EHR-
Coding Systems- Benefits of EHR- Barrier to Adopting HER Challenges-Phenotyping
Algorithms.
Unit II
Image Analysis
Biomedical Image Analysis- Mining of Sensor Data in Healthcare- Biomedical Signal
Analysis- Genomic Data Analysis for Personalized Medicine.

Unit III
Data Analytics
Natural Language Processing and Data Mining for Clinical Text- Mining the Biomedical
Social Media Analytics for Healthcare.

Unit IV
Advanced Data Analytics
Advanced Data Analytics for Healthcare– Review of Clinical Prediction Models- Temporal
Data Mining for Healthcare Data- Visual Analytics for Healthcare- Predictive 53 Models for
Integrating Clinical and Genomic Data- Information Retrieval for Healthcare- Data
Publishing Methods in Healthcare.

Unit V
Applications
Applications and Practical Systems for Healthcare– Data Analytics for Pervasive Health-
Fraud Detection in Healthcare- Data Analytics for Pharmaceutical Discoveries- Clinical
Decision Support Systems- Computer-Assisted Medical Image Analysis Systems- Mobile
Imaging and Analytics for Biomedical Data.

TEXT BOOKS

 Chandan K. Reddy and Charu C Aggarwal, “Healthcare data analytics”, Taylor &
Francis, 2015.

REFERENCE BOOKS

 Hui Yang and Eva K. Lee, “Healthcare Analytics: From Data to Knowledge to
Healthcare Improvement, Wiley, 2016.
SEMESTER – II Hours/week: 3
P__2901 Credits :2

CROSS DISCIPLINARY: DATA VISUALIZATION

[ TO BE OFFERED TO STUDENTS FROM OTHER SCHOOLS]

UNIT I- Introduction to Tableau (9 Hours)

Introducing real time dashboards – creating real time dashboards with Tableau – build a
Tableau dashboard – real time dashboard updates in Tableau – organizing your Tableau
dashboard – formatting your Tableau dashboard – interactive Tableau dashboard – Tableau
dashboard starters – Tableau dashboard extensions – Tableau dashboards and story points –
sharing your Tableau dashboard
UNIT II- Data Visualization Concepts (9 Hours)
Storytelling process – interpreting context – analysis types – who – what – and how of
storytelling – Visualization for storytelling – –Graphical tools for data elaboration –
storytelling scenarios – storyboarding – Visual selection – slope graphs – bar charts and types
of bar charts – clutter and clutter elimination – Gestalt principle – story design best practices
– tools for storytelling – Decluttering – crafting visual data – visual design concerns –
storytelling with power BI – model visual and Tableau
UNIT III- Data Dashboards using Tablet (9 Hours)
Introducing real time dashboards – creating real time – dashboards with Tableau – build a
Tableau dashboard – real time dashboard updates in Tableau – organizing your Tableau
dashboard – formatting your Tableau dashboard– interactive Tableau dashboard – Tableau
dashboard starters – Tableau dashboard extensions – Tableau dashboards and story points –
sharing your tableau dashboard.
UNIT IV- Open Source Data Visualization with Seaborn (9 Hours)
Introduction to Seaborn – install Seaborn – Simple Univariate distributions – configure
univariate – distribution plots – Simple Bivariate distributions – explore different types of –
Bivariate distributions – analyse multiple variable pairs – Regression plots – themes and –
styles in seaborn – searching for patterns in a dataset – configuring plot aesthetics – normal
distribution and outliers – distributions within categories-part –distributions within
categoriespart – analysing categories with facet grids - part – analysing categories with facet
grids-part – introducing colour palettes – using colour palettes
UNIT V- Open Source Data Visualization with Matplotlib, Bokeh And Pygal (9 Hours)
An Introduction To Matplotlib – analysing Data Using NumPy and Pandas – visualizing –
Univariate and Bivariate distributions – summary statistics using native – Python functions –
Summary Statistics using NumPy – summary statistics using the SciPy library – Correlation
and covariance – Z-score – relevance of data visualization for business – libraries for data
visualization in python – Python data visualization environment – configuration – matplotlib
libraries for visualization – bar chart using ggplot – bokeh and pygal – select visualization
libraries – interactive graphs and image files – plot graphs – multiple lines in graphs – using
scatter plots – using line graphs – using bar – charts – using box and whisker plots – using
histograms – using a bubble plot – chart types – stacked bar plot – animate plots with
matplotlib – plotting in Jupyter notebook

TEXTBOOKS:
• Fundamentals of Data Visualization, By Claus O. Wilke, April 2019
• Visual Analytics with Tableau, By Alexander Loth, May 2019
SEMESTER – III Hours/week: 4
PDS3501 Credits :4

MULTIVARIATE TECHNIQUES FOR DATA ANALYTICS

.
Unit – I: Introduction to Multivariate Techniques
Measurement Scales( Metric and Non-metric Measurement Scles) – Classification of
Multivariate Techniques( Dependence and Inter-dependence Techniques) – Applications of
Multivariate Techniques in different disciplines.

Unit – II: Factor Analysis

Introduction to Factor Analysis – Meaning, Objectives and Assumptions – Designing a
Factor Analysis Study – Deriving Factors – Assessing Overall Factors – Validation of Factor
Analysis.

Unit – III: Cluster Analysis

Introduction to Cluster Analysis – Objectives and Assumptions – Research Design in Cluster
Analysis – Hierarchical and Non-hierarchical Methods – Interpretation of Clusters –
Validation of Profiling of Clusters.

Unit – IV: Discriminant Analysis

Introduction to Discriminant Analysis – Concepts, Objectives and Applications – Procedure
for conducting Discriminant Analysis – Stepwise Discriminant Analysis – Mahalanobis
Procedure – Logit Model.

Unit – V: Principal Component Analysis

Dimensionality Reduction – Deriving Orthogonal Projections – Lower Dimensional
Subspaces – Characterization through Singular Value Decomposition and Eigenvalue
Analysis – Rayleigh Quotient – Kernel PCA – Functional PCA.

REFERENCES:
1. Joseph F Hair, William C Black etal , “Multivariate Data Analysis” , Pearson
Education, 7th edition, 2013.
2. T. W. Anderson , “An Introduction to Multivariate Statistical Analysis, 3rd Edition”,
Wiley, 2003.
3. William r Dillon, John Wiley & sons, “Multivariate Analysis methods and
applications”, Wiley, 1984.
4. Naresh K Malhotra, Satyabhusan Dash, “Marketing Research Anapplied
Orientation”, Pearson, 2011.
SEMESTER – III Hours/week: 4
PDS3502 Credits :4

DEEP LEARNING
.
Unit – I: Artificial Neural Networks
The Neuron – Activation Function – Gradient Descent – Stochastic Gradient Descent – Back
Propagation – Business Problem.

Unit – II: Convolutional Neural Networks

Convolution Operation – ReLU layer – Pooling – Flattening – Full Conversion Layer –
Softmax and Cross-Entropy.

Unit – III: Recurrent Neural Networks

RNN intuition – Tackling Vanishing Gradient Problem – Long Short-Term Memory –
Building a RNN – Evaluating the RNN – Improving the RNN – Tuning the RNN.

Unit – IV: Boltzmann Machines

Introduction to Boltzmann Machine – Energy-Based Models – Restricted Boltzmann
Machine – Contrastive Divergence – Deep Belief Networks – Deep Boltzmann Machine.

Unit – V: Computer Vision

Viola-Jones Algorithm – Haar-like Features – Integral Image – Training Classifiers –
Adaptive Boosting – Cascading – Face Detection with Open CV.

REFERENCES:
1. Francois Challot, “ Deep learning with Python”, Manning, 2017.
2. Deep Learning Illustrated: A Visual, Interactive Guide to Artificial Intelligence,By
Jon Krohn, Grant Beyleveld and Aglaé Bassens, September 2019
3. Ian Goodfellow, “Deep Learning”, MIT Press, 2017.
4. Josh Patterson, “Deep Learning: A Practitioner’s Approach”, PACKT, 2017.
5. Dipayan Dev, “ Deep Learning with Hadoop”, PACKT, 2017.
6. Hugo Larochelle’s Video Lectures on Deep Learning
SEMESTER – III Hours/week: 4
PDS3503 Credits :4
DEEP LEARNING - LAB

LIST OF EXERCISES:
1. Setting up the Spyder IDE Environment and Executing a Python Program
2. Installing Keras, Tensorflow and Pytorch libraries and making use of them
3. Artificial Neural Networks
4. Convolutional Neural Networks
5. Image Transformations
6. Image Gradients and Edge Detection
7. Image Contours
8. Image Segmentation
9. Harris Corner Detection
10. Face Detection using Haar Cascades
11. Chatbot Creation
SEMESTER – III Hours/week: 4

PDS3504 Credits :4
CLOUD COMPUTING
Unit – I: Introduction
Evolution of Cloud Computing –Essential Characteristics of cloud computing – Operational
models such as private, dedicated, virtual private, community, hybrid and public cloud –
Service models such as IaaS, PaaS and SaaS – Governance and Change Management –
Business drivers, metrics and typical use cases. Example cloud vendors – Google cloud
platform, Amazon AWS, Microsoft Azure, Pivotal cloud foundry and Open Stack.
Unit – II: Infrastructure Services
Basics of Virtual Machines - Taxonomy of Virtual Machines. Virtualization Architectures.
Challenges with Dynamic Infrastructure - Principles of Infrastructure as Code -
Considerations for Infrastructure Services and Tools - Monitoring: Alerting, Metrics, and
Logging - Service Discovery - Server Provisioning via Templates - Patterns and Practices for
Continuous Deployment - Organizing Infrastructure and Testing Infrastructure - Change
Management Pipelines for Infrastructure.
Unit – III: Platform Engineering
Cloud Native Design and Microservices– Containerized - Dynamically orchestrated design –
Continuous delivery - Support for a variety of client devices – Monolithic vs Microservices
Architecture - Characteristics of microservice architecture – 12 factor application design -
Considering service granularity – Scalable Services - Sharing dependencies between
microservices - Stateless versus Stateful microservices - Service discovery – Service Registry
– Performance Considerations.
Unit – IV: Serverless Architecture and DevOps
Function as a Service (FaaS) - Backend as a Service (BaaS) - Advantages of serverless
architectures - Taking a hybrid approach to serverless architecture - Function deployment and
Function invocation. Introduction to DevOps - The Deployment Pipeline - The Overall
Architecture - Building and Testing - Deployment - Crosscutting Concerns such as
Monitoring, Scalability, Repeatability, Reliability, Recoverability, Interoperability,
Testability, and Modifiability,
Unit – V: Cloud Security
Security Considerations – STRIDE Threat Model - Cloud Security Challenges – Cloud
specific Cryptographic Techniques – CIA Triad – Security by Design – Common Security
Risks - Risk Management – Security Monitoring – Security Architecture Design – Data
Security – Application Security – Virtual Machine Security.
REFERENCES:
1. Dr.AnandNayyar, (2019), “Handbook of Cloud Computing”, BPB
2. Mastering Azure Machine Learning, By Christoph Korner and Kaijisse
Waaijer, April 2020
3. Hands-On Machine Learning on Google Cloud Platform,By Giuseppe
Ciaburro, V Kishore Ayyadevara and Alexis Perrier, April 2018
4. Learning Path: AWS Certified Machine Learning-Specialty ML, By Noah
Gift, April 2019
5. Software Architect's Handbook, by Joseph Ingeno, Published by Packt
Publishing, 2018
6. Architecting Cloud Computing Solutions by Scott Goessling, Kevin L.
Jackson, Publisher: Packt Publishing, Release Date: May 2018
7. Microservices: Flexible Software Architecture, by Eberhard Wolff, Publisher:
Addison-Wesley Professional, Release Date: October 2016
SEMESTER – III Hours/week: 4
PDS3601 Credits :3

ELECTIVE 2A: NATURAL LANGUAGE PROCESSING

.
Unit – I: Introduction
Overview: Origins and challenges of NLP- Theory of Language -Features of Indian
Languages – Issues in Font –Models and Algorithms- NLP Applications.

UNIT II - MORPHOLOGY AND PARTS-OF-SPEECH

Phonology – Computational Phonology - Words and Morphemes – Segmentation –
Categorization and Lemmatisation – Word Form Recognition – Valency - Agreement -
Regular Expressions – Finite State Automata – Morphology- Morphological issues of Indian
Languages – Transliteration.

UNIT III - PROBABILISTIC MODELS

Probabilistic Models of Pronunciation and Spelling – Weighted Automata – N- Grams –
Corpus Analysis – Smoothing – Entropy - Parts-of-Speech – Taggers – Rule based – Hidden
Markov Models – Speech Recognition.

UNIT IV - SYNTAX
Basic Concepts of Syntax – Parsing Techniques – General Grammar rules for Indian
Languages – Context Free Grammar – Parsing with Context Free Grammars – Top Down
Parser – Earley Algorithm – Features and Unification - Lexicalised and Probabilistic Parsing.

UNIT V - SEMANTICS AND PRAGMATICS (6 hours) Representing Meaning –

Computational Representation – Meaning Structure of Language – Semantic Analysis –
Lexical Semantics – WordNet – Pragmatics – Discourse – Reference Resolution – Text
Coherence – Dialogue Conversational Agents.

REFERENCES:

1. Daniel Jurafskey and James H. Martin “Speech and Language Processing”, Prentice
Hall, 2009.
2. Christopher D.Manning and Hinrich Schutze, “Foundation of Statistical Natural
Language Processing”, MIT Press, 1999.
3. Ronald Hausser, “Foundations of Computational Linguistics”, Springer-Verleg, 1999.
4. James Allen, “Natural Language Understanding”, Benjamin/Cummings Publishing
Co. 1995.
5.Applied Natural Language Processing with Python: Implementing Machine Learning
and Deep Learning Algorithms for Natural Language Processing,By Taweh Beysolow
II, September 2018
SEMESTER – III Hours/week: 4
PDS3602 Credits :3

ELECTIVE 2B: COMPUTER VISION

Here is a rough outline of topics and the number of lectures to be spent on each topic:

 Image formation / projective geometry / lighting (3 lectures)

 Practical linear algebra (2 lectures)
 Image processing / descriptors (2 lectures)
 Image warping (2 lectures)
 Linear models + optimization (2 lectures)
 Neural networks (3 lectures)
 Applications of neural networks (3 lectures)
 Motion and flow (2 lectures)
 Single-view geometry (2 lectures)
 Multi-view geometry (3 lectures)
 Applications (3 lectures)

Textbooks:

 Computer Vision: Algorithms and Applications by Richard Szeliski.

Available for free online.
 Computer Vision: A Modern Approach (Second Edition) by David Forsyth and
Jean Ponce. Available for free online.
 Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani, and Jerome
Friedman. Available for free online (Warning: Direct PDF link).
 Multiple View Geometry in Computer Vision (Second Edition) by Richard
Hartley and Andrew Zisserman. Available for free online through the UM
Library (Login required).