Skip to main content

๐ŸŽ“ M.Tech โ€“ ๐™ˆ๐™–๐™˜๐™๐™ž๐™ฃ๐™š ๐™‡๐™š๐™–๐™ง๐™ฃ๐™ž๐™ฃ๐™œ & ๐˜ฟ๐™š๐™š๐™ฅ ๐™‡๐™š๐™–๐™ง๐™ฃ๐™ž๐™ฃ๐™œ

Master of Technology in Machine Learning & Deep Learning
๐Ÿซ Malla Reddy University
๐Ÿท๏ธ Code: MR22

๐Ÿ“˜ Year - Iโ€‹

#๐Ÿ“– Semester I#๐Ÿ“— Semester II
โ‘ ๐Ÿง  Machine Learning (2CS0205)โ‘ ๐Ÿง  Deep Learning (2CS0206)
โ‘ก๐Ÿ“Š Statistical Machine Learning (2BS0103)โ‘ก๐Ÿค– Advanced Machine Learning (2CS0211)
โ‘ข๐Ÿ—ฃ๏ธ Natural Language Processing (2CS0213)โ‘ขโš›๏ธ Quantum Computing (2BS0131)
โ‘ฃ๐Ÿ“ˆ Business Intelligence & Analytics (2CS0218)โ‘ฃโ˜๏ธ Cloud Computing (2CS0207)
โ‘ค๐Ÿงฎ Advanced Algorithms (2CS0201)โ‘ค๐Ÿ—ƒ๏ธ Data Warehouse & Data Mining (2CS0203)
โ‘ฅ๐ŸŒ Full Stack Development (2CS0204)โ‘ฅ๐Ÿง‘โ€๐Ÿ’ป Software Engineering (2CS0214)

๐Ÿ“™ Year - IIโ€‹

#๐Ÿ“˜ Semester III#๐Ÿ“— Semester IV
โ‘ ๐Ÿงต Big Data Analytics (2CS0202)โ‘ ๐Ÿš€ Startup Internship
โ‘ก๐Ÿงญ Reinforcement Learning (2CS0215)โ‘ก๐Ÿ› ๏ธ Project Development Phase-2
โ‘ข๐Ÿ”ฌ Project Development Phase-1

Semester Iโ€‹

1. Machine Learningโ€‹

PREREQUISITES: Mathematical Foundations for Machine Learning, Data Mining

COURSE OBJECTIVES:

  • To Understand the formulation of well-specified machine learning problems
  • To introduce students to the basic concepts and techniques of Machine Learning.
  • To develop skills of using recent machine learning software for solving practical problems.
  • To gain experience of doing independent study and research.
  • Identify examples of the ethical responsibilities of an ML

COURSE OUTCOMES:

  • To Implement and analyse existing learning algorithms, including well-studied methods for classification, regression, structured prediction, clustering, and representation learning.
  • ToIntegrate multiple facets of practical machine learning in a single system: data
  • Pre-processing, learning, regularization and model selection
  • ToEmploy probability, statistics, calculus, linear algebra, and optimization in order to Develop new predictive models or learning methods
  • To Design experiments to evaluate and compare different machine learning techniques on Real- World problems

UNIT I

Linear Regression: Introduction, Fitting a Line, Handling Interactive Effects, Fitting a Nonlinear Relationship, Reducing Variance with Regularization.[BOOK- 1]

Logistic Regression: Introduction, Training a Binary Classifier, Training a Multiclass Classifier, Reducing Variance Through Regularization. [BOOK- 1]

  • Case Study 1: Predicting House Prices with Linear Regression
  • Case Study 2 : Logistic Regression [In this Case study to working with a fake advertising data set, indicating whether or not a particular internet user clicked on an Advertisement. We will try to create a model that will predict whether or not they will click on an ad based off the features of that user.]

UNIT - II

Trees & Forests: Introduction, Training a Decision Tree Classifier , Training a Decision Tree Regressor Visualizing a Decision Tree Model , Training a Random Forest Classifier ,Training a Random Forest Regressor ,Identifying Important Features in Random Forests , Selecting Important Features in Random Forests , Handling Imbalanced Classes, Controlling Tree Size , Improving Performance Through Boosting , Evaluating Random Forests with Out-of-Bag Errors. [BOOK- 1]

K-Nearest Neighbors: Introduction, Finding an Observationโ€™s Nearest Neighbors, Creating a K-Nearest Neighbor Classifier, Identifying the Best Neighborhood Size, Creating a Radius-Based Nearest Neighbor Classifier. [BOOK- 1]

  • Case Study 1 : Decision Tree Classifier
  • Case Study 2: Making Predictions with KNN

UNIT - III

Support Vector Machines: Introduction, Training a Linear Classifier , Handling Linearly Inseparable Classes Using Kernels , Creating Predicted Probabilities , Identifying Support Vectors , Handling Imbalanced Classes.

Naive Bayes: Introduction, Training a Classifier for Continuous Features , Training a Classifier for Discrete & Count Features, Training a Naive Bayes Classifier for Binary Features, Calibrating Predicted Probabilities. [BOOK- 1]

  • Case Study 1: First SVM for Classification: We are using the โ€œSocial Network Adsโ€ dataset on kaggle here is the link of this dataset Social_Network_Ads
  • Case study 2: Second SVM for Regression: We are using the โ€œPosition Salariesโ€ dataset on kaggle here is the link of this dataset Position_Salaries Case Study 3: Naive Bayes Classifier in Iris Flower Species Dataset.

UNIT - IV

Clustering: Introduction, Clustering Using K-Means, Speeding Up K-Means Clustering, Clustering Using Mean shift, Clustering Using DBSCAN, Clustering Using Hierarchical Merging. [BOOK- 1]

  • Case study: Clustering Using DBSCAN

UNIT - V

Bagging, Bootstrap Method, Bootstrap Aggregation (Bagging), Preparing Data For Bagged CART , Boosting & AdaBoost [BOOK- 2]

  • Case study: Making Predictions with AdaBoost

Booksโ€‹

  1. Machine Learning with Python Cookbook by Chris Albon, OREILY 2018.
  2. Master Machine Learning Algorithms by Jason Brownlee, Machine learning Masery, 2016.
  3. Machine Learning, Tom Mitchell , McGraw Hill, 1997
  4. Kevin Murphy, Machine Learning: A Probabilistic Perspective, MIT Press, 2012.

2. Statistical Machine Learningโ€‹

COURSE OBJECTIVES:

  • To understand the concepts of the probability and probability distributions associated with different types of random variables.
  • To fit a suitable probability distributions.
  • To understand the Concept of correlation for a bivariate distributions.
  • To understand and to formulate the various regression models of statistical data.
  • To understand the various sampling methods which are useful for computer science engineers

COURSE OUTCOMES: After learning the contents of this course the students must be able to:

  • Understand and able to write down various probability distributions for different types of random variables
  • To identify various probability distributions (discrete and continuous) for given phenomena.
  • To determine the nature of association between the variables of a bivariate data
  • To construct various regression models and estimation of parameter of the model
  • Different types of sampling methods which are useful for computer science and engineers.

COURSE OUTCOMES:

  • To tag a given text with basic Language features
  • To design an innovative application using NLP components
  • To implement a rule based system to tackle morphology/syntax of a language
  • To design a tag set to be used for statistical processing for real-time applications
  • To compare and contrast the use of different statistical approaches for different types of NLP applications.

UNIT โ€“ I

Review of probability theory โ€“ Conditional Probability โ€“ Bayes Rule โ€“ Random variables โ€“ Probability distributions โ€“ Joint, Marginal & conditional Probability distributions โ€“ Generating functions

UNIT โ€“ II

Review of Some Discrete & Continuous Probability Distributions: Binomial, Poisson (General & Truncated Distributions) Exponential, Normal Distributions (General & Truncated).

UNIT โ€“ III

Bivariate distributions: Bivariate data โ€“ Concept of variance & co-variance โ€“ Correlation (Simple, Partial & Auto Correlation) โ€“ Simple Problems.

UNIT โ€“ IV

Regression: linear statistical models; multiple linear regression: inference technique for the general linear model, generalized linear models: inference procedures, special case of generalized linear models leading to logistic regression & log linear models;

UNIT โ€“ V

Sampling Methods: Basic sampling algorithms, rejection sampling, adaptive rejection sampling, sampling & the EM algorithm, Markhov chain, Monte Carlo, Gibbs sampling, slice sampling.

Booksโ€‹

  1. Douglas C. Montgomery & George C. Runger, โ€œApplied Statistics & Probability for Engineersโ€, Third Edition, John Wiley & Sons Inc., 2003.
  2. Krzanowski, W. J., An Introduction to Statistical Modeling, Wiley (2010).
  3. David Forsyth, โ€œProbability & Statistics for Computer Scienceโ€, Springer international publishing, 2018
  4. T.Veerarajan , โ€œProbability, Statistics & Random Processesโ€ Tata McGraw-Hill,Education
  5. V K Rohatgi An Introduction to Probability & stiatics 3e, Wiley

3. Natural Language Processingโ€‹

PREREQUISITES: Probability and statistics, Programming and data structures

COURSE OBJECTIVES:

  • To learn the fundamentals of natural language processing.
  • To understand the use of CFG and PCFG in NLP.
  • To understand the role of semantics of sentences and pragmatics.
  • To apply the NLP techniques to IR applications.
  • To understand NLP Analysis and Lexical Analysis.

COURSE OUTCOMES:

  • To tag a given text with basic Language features
  • To design an innovative application using NLP components
  • To implement a rule based system to tackle morphology/syntax of a language
  • To design a tag set to be used for statistical processing for real-time applications
  • To compare and contrast the use of different statistical approaches for different types of NLP applications.

UNIT - I

INTRODUCTION: Origins & challenges of NLP โ€“ Language Modelling: Grammar-based LM, Statistical LM Regular Expressions, Finite-State Automata โ€“ English Morphology, Transducers for lexicon & rules, Tokenization, Detecting & Correcting Spelling Errors, Minimum Edit Distance[BOOK-1] .

UNIT - II

WORD LEVEL ANALYSIS: Unsmoothed N-grams, Evaluating N-grams, Smoothing, Interpolation & Backoff โ€“ Word Classes, Partof-Speech Tagging, Rule-based, Stochastic & Transformation-based tagging, Issues in PoS tagging โ€“ Hidden Markov & Maximum Entropy model [BOOK-2].

UNIT - III

**SYNTACTIC ANALYSIS:**Context-Free Grammars, Grammar rules for English, Treebanks, Normal Forms for grammar โ€“ Dependency Grammar โ€“ Syntactic Parsing, Ambiguity, Dynamic Programming parsing โ€“ Shallow parsing โ€“ Probabilistic CFG, Probabilistic CYK, Probabilistic Lexicalized CFGs - Feature structures, Unification of feature structures NLP in Information Retrieval, Cross-Lingual IR.[BOOK-3].

UNIT โ€“ IV

Requirements for representation, First-Order Logic, Description Logics โ€“ Syntax-Driven Semantic analysis, Semantic attachments โ€“ Word Senses, Relations between Senses, Thematic Roles, selectional restrictions โ€“ Word Sense Disambiguation, WSD using Supervised, Dictionary & Thesaurus, Bootstrapping methods โ€“ Word Similarity using Thesaurus & Distributional methods.[BOOK-4].

UNIT - V

DISCOURSE ANALYSIS AND LEXICAL RESOURCES: Discourse segmentation, Coherence โ€“ Reference Phenomena, Anaphora Resolution using Hobbs & Centering Algorithm โ€“ Coreference Resolution โ€“ Resources: Porter Stemmer, Lemmatizer, Penn Treebank, Brill's Tagger, WordNet, PropBank, FrameNet, Brown Corpus, British National Corpus (BNC), Neural Machine Translation. [BOOK-5].

Booksโ€‹

  1. Daniel Jurafsky, James H. Martinโ€•Speech & Language Processing: An Introduction to Natural Language Processing, Computational Linguistics & Speech, Pearson Publication, 2014.
  2. Steven Bird, Ewan Klein & Edward Loper, Natural Language Processing with Pythonโ€–, First Edition, O Reilly Media, 2009.
  3. Christopher D., & Hinrich Schรผtze -Foundations of Statistical Natural Language Processing, Manning, Cambridge, MA: MIT Press 3 2015.
  4. James Allen. The Benjamin/Cummings -Natural Language Understanding, Publishing Company Inc.. 2014.
  5. Steven Bird, Ewan Klein, & Edward Loper- Natural Language Processing with Python โ€“ Analyzing Text with the Natural Language Toolkit Pearson Publications ,2015.

4. Business Intelligence & Analyticsโ€‹

PREREQUISITES: Data Visualization, Data Mining.

COURSE OBJECTIVES:

  • Be exposed with the basic rudiments of business intelligence system.
  • Understand the modeling aspects behind Business Intelligence.
  • Understand of the business intelligence life cycle and the techniques used in it.
  • Be exposed with different data analysis tools and techniques.
  • To learn about business intelligence applications.

COURSE OUTCOMES:

  • After completion of the course, the students will be able to Explain the fundamentals of business intelligence.
  • Link data mining with business intelligence.
  • Apply various modeling techniques.
  • Explain the data analysis and knowledge delivery stages.
  • Apply business intelligence methods to various situations.

UNIT - I

BUSINESS INTELLIGENCE: Effective & timely decisions โ€“ Data, information & knowledge โ€“ Role of mathematical models โ€“ Business intelligence architectures: Cycle of a business intelligence analysis โ€“ Enabling factors in business intelligence projects โ€“ Development of a business intelligence system โ€“ Ethics & business intelligence.[BOOK-1]

UNIT - II

KNOWLEDGE DELIVERY: The business intelligence user types, Standard reports, Interactive Analysis & AdHocQuerying, Parameterized Reports & Self-Service Reporting, dimensional analysis, Alerts/Notifications, Visualization: Charts, Graphs, Widgets, Scorecards & Dashboards, Geographic Visualization, Integrated Analytics, Considerations: Optimizing the Presentation for the Right Message. [BOOK-2]

UNIT - III

EFFICIENCY: Efficiency measures โ€“ The CCR model: Definition of target objectives- Peer groups โ€“ Identification of good operating practices; cross efficiency analysis โ€“ virtual inputs & outputs โ€“ Other models. Pattern matching โ€“cluster analysis, outlier analysis. [BOOK-3]

UNIT - IV

FRAMEWORKS: Marketing models โ€“ Logistic & Production models โ€“ Case studies. [BOOK-1]

UNIT - V

FUTURE OF BUSINESS INTELLIGENCE: Future of business intelligence โ€“ Emerging Technologies, Machine Learning, Predicting the Future, BI Search & Text Analytics โ€“ Advanced Visualization โ€“ Rich Report, Future beyond Technology. [BOOK-3]

Booksโ€‹

  1. Carlo Vercellis, โ€œBusiness Intelligence: Data Mining & Optimization for Decision Makingโ€, Wiley Publications, 2009.
  2. Efraim Turban, Ramesh Sharda, Dursun Delen, โ€œDecision Support & Business Intelligence Systemsโ€, 9 th Edition, Pearson 2013.
  3. Larissa T. Moss, S. Atre, โ€œBusiness Intelligence Roadmap: The Complete Project Lifecycle of Decision Makingโ€, Addison Wesley.
  4. David Loshin Morgan, Kaufman, โ€œBusiness Intelligence: The Savvy Managerโ€Ÿs Guideโ€, Second Edition, 2012.
  5. Ralph Kimball , Margy Ross , Warren Thornthwaite, Joy Mundy, Bob Becker, โ€œThe Data Warehouse Lifecycle Toolkitโ€, Wiley Publication Inc.,2007.

5. Advanced Algorithmsโ€‹

PREREQUISITES: Data structures, Design and analysis of algorithms.

COURSE OBJECTIVES:

  • To provide the foundations of the practical implementation and usage of Algorithms and Data Structures.
  • To ensure that the student evolves into a competent programmer capable of designing.
  • To analyze implementations of algorithms and data structures for different kinds of problems.
  • To expose the student to the algorithm analysis techniques, to the theory of reductions.
  • To know the classification of problems into complexity classes like NP.

COURSE OUTCOMES:

  • Design and analyze programming problem statements.
  • Understand elementary data structures and graph algorithms.
  • Understand the necessary mathematical abstraction to solve problems.
  • Come up with analysis of efficiency and proofs of correctness.
  • Comprehend and select algorithm design approaches in a problem specific manner.

UNIT I

Introduction: Algorithms, Performance analysis- Space complexity, Time Complexity, Asymptotic notation- Big oh notation, omega notation, theta notation & little oh notation. Treesโ€“ Basics of trees & binary trees, Representation of trees & Binary trees. [BOOK-1]

UNIT II

Graph algorithms: Breadth First Search (BFS), Applications of BFS, Depth First Search (DFS), Applications of DFS: Topological sort, Cycle detection. Disjoint set data structure: Disjoint set operations, Union- find Algorithms, Connected components. [BOOK-1]

UNIT III

Divide โ€“ & โ€“ Conquer: - General Method, Binary Search, Quick Sort, Merge sort. Back Tracking: General Method, N โ€“ Queenโ€™s Problem, Graph Coloring. [BOOK-3]

UNIT IV

Greedy Method- General Method, Minimum Cost Spanning Trees, Single Source Shortest Path. Dynamic Programming - General Method, All Pairs Shortest Path, 0 /1 Knapsack problem, Traveling Sales Personโ€™s Problem. [BOOK-3]

UNIT V

Branch & Bound: General method, applications- Travelling sales person problem, 0/1 Knapsack problem-LC branch & Bound solution. NP-Hard & NP-Complete Problems: P-Class & NP-Class problems, Non deterministic algorithms, NP-Hard & NPComplete classes. [BOOK-3]

Booksโ€‹

  1. Fundamentals of Computer Algorithms by Ellis Horowitz, Sartaj Sahni & Sanguthevar Rajasekaran, 2nd edition, University Press.
  2. Data Structures & Algorithms Using C++ by Ananda Rao Akepogu & Radhika Raju Palagiri, Pearson Education, 2010.
  3. Design & Analysis of Algorithms by E. Horowitz, S. Sahani, 3rd Edition, Galgotia.

6. Full Stack Developmentโ€‹

COURSE OBJECTIVES:

  • Design static web page using Markup languages.
  • Design and implement web pages using style sheets.
  • Implement with java script web applications with dynamic web pages.
  • Understand working of application using Angular JS Framework, React JS, Node JS.
  • Understand databases MongoDB with NodeJS and services of MongoDB.

COURSE OUTCOMES:

  • Design user interactions on web pages.
  • Develop back end website applications.
  • Create servers and databases for functionality.
  • Develop adaptive content for multiple devices (cell phone, tablets, etc.)Ensure cross-platform optimization for mobile phones.
  • Ensure responsiveness of applications.

UNIT I

HTML: Tags, Attribute & Elements, Doctype Element, Comments, Headings, Paragraphs, & Formatting Text, Lists & Links, Images & Tables. CSS: Applying CSS to HTML, Selectors, Properties & Values, Colors & Backgrounds, Margins, Padding, & Borders, CSS Text & Font Properties JavaScript: Introduction, Variables & Operators, Data Types & Num Type Conversion, Math & String Manipulation, Objects & Arrays, Date & Time, Conditional Statements, Switch Case, Looping in Java script, Functions, Developing web site using CSS. [BOOK-1]

UNIT II

Back-End Definitions: Node.js, NoSQL & MongoDB, Cloud Computing, HTTP Requests & Responses, RESTful API, Local Setup, Local HTTP Servers, Cloud Setup, jQuery & Parse.com, Definitions , jQuery Functions, Twitter Bootstrap, An Example Using a Third-Party API (Twitter) & jQuery, Message Board with Parse.com Overview, Developing online application using jquery. [BOOK-4]

UNIT III

Introduction to Backbone.js: Setting Up Backbone.js App from Scratch, Working with Backbone.js Collections, Backbone.js Event Binding, Backbone.js Views & Sub views with Underscore.js, Refactoring Backbone.js Code, AMD & Require.js for Backbone.js Development, Require.js for Backbone.js Production, Super Simple Backbone.js Starter Kit, Message Board with Parse.com: JavaScript SDK & Backbone.js Version, Taking Message Board Further, Application Development using backbone.js. [BOOK-4]

UNIT IV

Node Js : Intro to Node.js, Building โ€œHello Worldโ€ in Node.js, Node.js Core Modules, HTTP, Util, Query string, url,fs, npm Node Package Manager, Deploying "Hello World" to Paas, Deploying to Windows Azure, Deploying to Heroku, Message Board with Node.js: Memory Store Version, Unit Testing Node.js, Developing http application using node.js [BOOK-4]

UNIT V Mongo DB: MongoDB Shell, BSON, MongoDB Native Driver, MongoDB on Heroku: MongoLab, Message Board: MongoDB Version, Adding CORS for Different Domain Deployment, Message Board UI, Message Board API, Same Domain Deployment Server, Deployment to Amazon Web Services, Developing Backend application using MongoDB. [Reference 4]

Booksโ€‹

  1. Java Script &jQuery the missing manual, 2nd Edition, David sawyer mcfarland, Oโ€™Reilly, 2011.
  2. Web Design with HTML, CSS, JavaScript & JQuery Set Book by Jon Duckett
  3. Professional JavaScript for Web Developers Book by Nicholas C. Zakas
  4. Learning PHP, MySQL, JavaScript, CSS & HTML5: A Step-by-Step Guide to Creating Dynamic Websites by Robin Nixon
  5. Full Stack JavaScript: Learn Backbone.js, Node.js & MongoDB. Copyright ยฉ 2015 BY AZAT MARDAN

Semester IIโ€‹

1. Deep Learningโ€‹

UNIT โ€“ I

History of Deep Learning, McCulloch Pitts Neuron, Perceptron, Perceptron Learning Algorithm, Multilayer Perceptronโ€™s (MLPs), Representation Power of MLPs, Sigmoid Neurons, Feed forward Neural Networks, Representation Power of Feed forward Neural Networks, Back propagation. . [BOOK-2]

Case study:

  1. Develop a handwriting recognition system using MLPs & back propagation.
  2. Build an image classification system using a feed-forward neural network with sigmoid activation functions.

UNIT - II

Gradient Descent (GD), Momentum Based GD, Nesterov Accelerated GD, Stochastic GD, AdaGrad, RMSProp, Adam, Eigenvalues & Eigen vectors, Eigen value Decomposition, Basis, Principal Component Analysis & its interpretations, Singular Value Decomposition. [BOOK-1]

Case study:

  1. Develop a recommendation system using matrix factorization & Stochastic Gradient Descent (SGD).
  2. Build an image compression system using Principal Component Analysis (PCA) & Singular Value Decomposition (SVD).

UNIT - III

Auto encoders & relation to PCA, Denoising auto encoders, sparse auto encoders, Contractive auto encoders, Regularization: Bias Variance Tradeoff, L2 regularization, early stopping, Dataset augmentation, Parameter sharing & tying, Injecting noise at input, Dropout. [BOOK-2]

Case study:

  1. Build a fraud detection system using denoising auto encoders.
  2. Develop an image classification system using convolutional neural networks (CNNs) & data augmentation.

UNIT โ€“ IV

Greedy Layer wise Pre-training, Better activation functions, Better weight initialization methods, Batch Normalization, Learning Vectorial Representations of Words: Word2Vec. [BOOK-1]

Case study:

  1. Building a recommendation system using Word2Vec & Greedy Layer Wise Pre-Training.
  2. Developing a chat bot using better activation functions & batch normalization.

UNIT โ€“ V

Convolutional Neural Networks, Guided Back propagation, Recurrent Neural Networks, Back propagation through time (BPTT), GRU, LSTMs, Attention Mechanism, Attention over images, Case Study: AlexNet, GoogLeNet, ResNet, Deep Dream, Deep Art. [BOOK-3]

Case study:

  1. Developing a music recommendation system using a combination of Convolutional Neural Networks & Recurrent Neural Networks.
  2. Building a deep learning model to predict the risk of heart disease using Convolutional Neural Networks & Attention Mechanism.

Booksโ€‹

  1. Deep Learning, An MIT Press book, Ian Goodfellow & Yoshua Bengio & Aaron Courville deeplearningbook
  2. Neural Networks & Learning Machines, Simon Haykin, 3rd Edition, Pearson Prentice Hall.
  3. Hands-On Deep Learning Algorithms with Python: Master deep learning algorithms with extensive math by implementing them using Tensor Flow.

2. Advanced Machine Learningโ€‹

UNIT I:

Data Mining: Introduction & challenges. Association rule mining โ€“ apriori algorithm, FP Growth algorithm.

UNIT II:

Mining massive datasets: MapReduce (distributed file systems, complexity theory for mapreduce), Finding similar items โ€“ LSH, Link Analysis โ€“ Concept of Pagerank, Efficient computation of page rank.

UNIT III:

Recommender Systems: Review of linear algebra: eigen values, eigen vectors, SVD. Concept, Content based recommendations. Collaborative Filtering, Awareness of the Netflix Change.

UNIT IV:

Mining Social Network Graphs: Concept. Graph clustering. Graph partitioning, Overlapping communities, Simrank, Counting Triangles.

UNIT V:

Dimensionality Reduction: Principal component analysis. concepts of feature selection & reduction. Text representations, naive Bayes & multinomial models, clustering & latent space models, VC- dimension, structural risk minimization, margin methods, Introduction to Deep Learning.

Booksโ€‹

  1. โ€œData Mining: Concepts & Techniquesโ€. Wiley. 2nd or 3rd Edition

  2. โ€œMining of Massive Datasetsโ€. J. Leskovec, A. Rajaraman, J.D. Ullman. 3rd Edition. Cambridge University Press.

    REFERENCES:

  3. Josh Patterson & Adam Gibson, โ€œDeep learning: A practitioners approachโ€, O'Reilly Media, First Edition, 2017.

3. Quantum Computingโ€‹

Unit-I

Introduction to Quantum Computing: Introduction, types of computing- Classical & Quantum computing, History of quantum computing, need for quantum computers, Future of Quantum computing, Brief applications of Quantum computing-Molecular modelling & new materials, deep learning, cyber security, quantum neural networks & artificial intelligence.

Unit-II

Quantum Mechanics for Measurements: Complex vector spaces: Linear combination of vectors, complex conjugate, Inner Products & Hilbert space, Dirac notation Bra-Ket formalism, outer products, Representing Composite States in Quantum Mechanics, Representation of operators using matrices-The Pauli Operators, Hermitian & unitary operators, Postulates of Quantum Mechanics, Tensor products of vector spaces, Eigen values & Eigen Vectors,

Unit-III

Quantum Bit & Quantum Gates: Superposition & entanglement, Representation of qubits using Dirac & Bloch sphere, Types of quantum gates-Single qubit gates-Pauliโ€™s X, Y, Z, Hadamard gate (H-gate), Phase gate (S-gate); Multiple quantum gates: CNOT, CCNOT (Toffoli gate), SWAP gate.

Unit-IV

Quantum Algorithms: Deutschโ€™s Algorithm, The Deutschโ€“Jozsa Algorithm, Groverโ€™s Search Algorithm, Shorโ€™s Factoring Algorithm, Noise & error correction: Quantum error correction & quantum annealing.

Unit-V

Quantum Basic circuit programming using Qiskit: Introduction to Qiskit, IBM sign up, Quantum circuits, demonstration of gates in qiskit, compute the XOR, AND, NAND & OR gates using the NOT gate (expressed as x in Qiskit), the CNOT gate (expressed as cx in Qiskit) & the Toffoli gate (expressed as ccx in Qiskit).

Booksโ€‹

  1. Michael A. Nielsen & Isaac L. Chuang, Quantum computation & quantum information, Cambridge University Press, 2010.

4. Cloud Computingโ€‹

UNIT-I

Cloud Computing Overview: Origins of Cloud computing โ€“ Cloud components - Essential characteristics โ€“ On-demand self- service, Broad network access, Location independent resource pooling ,Rapid elasticity , Measured service, Comparing cloud providers with traditional IT service providers, Roots of cloud computing.

UNIT-II

Cloud Insights, Architectural influences โ€“ High-performance computing, Utility & Enterprise grid computing, Cloud scenarios โ€“ Benefits: scalability ,simplicity ,vendors ,security, Limitations โ€“ Sensitive information - Application development- security level of third party - security benefits, Regularity issues: Government policies.

UNIT-III

Cloud Architecture- Layers & Models, Layers in cloud architecture, Software as a Service (SaaS), features of SaaS & benefits, Platform as a Service ( PaaS ), features of PaaS & benefits, Infrastructure as a Service (IaaS), features of IaaS & benefits, Service providers, challenges & risks in cloud adoption. Cloud deployment model: Public clouds โ€“ Private clouds โ€“ Community clouds - Hybrid clouds- Advantages of Cloud computing.

UNIT-IV Cloud Simulators- CloudSim & GreenCloud, Introduction to Simulator, understanding Cloud Sim simulator, CloudSim Architecture(User code, CloudSim, GridSim, SimJava) Understanding Working platform for CloudSim, Introduction to GreenCloud.

UNIT -V Introduction to VMWare Simulator, Basics of VMWare, advantages of VMware virtualization, using Vmware workstation, creating virtual machines-understanding virtual machines, create a new virtual machine on local host, cloning virtual machines, virtualize a physical machine, starting & stopping a virtual machine.

Booksโ€‹

  1. Cloud computing a practical approach - Anthony T.Velte, Toby J. Velte Robert Elsenpeter,TATA McGraw- Hill, New Delhi โ€“ 2010.
  2. Cloud Computing: Web-Based Applications That Change the Way You Work & CollaborateOnline - Michael Miller - Que 2008.

REFERENCES:

  1. Cloud computing for dummies- Judith Hurwitz, Robin Bloor, Marcia Kaufman, FernHalper, Wiley Publishing, Inc, 2010.
  2. Cloud Computing (Principles & Paradigms), Edited by Rajkumar Buyya, James Broberg,Andrzej Goscinski, John Wiley & Sons, Inc. 2011

5. Data Warehouse & Data Miningโ€‹

UNIT I

Data Warehousing: Overview, Definition, Delivery Process, Difference between Database System & Data Warehouse, Multi-Dimensional Data Model, Data Cubes, Stars, Snow Flakes, Fact Constellations, Concept hierarchy, Process Architecture, 3 Tier Architecture, Data Marting.

UNIT II

Classification & Predictions: What is Classification & Prediction, Issues regarding Classification & prediction, Decision tree, Bayesian Classification, Classification by Back propagation, Multilayer feed- forward Neural Network, Back propagation Algorithm, Classification methods K-nearest neighbour classifiers, Genetic Algorithm.

Cluster Analysis: Data types in cluster analysis, Categories of clustering methods, Partitioning methods. Hierarchical Clustering- CURE & Chameleon, Density Based Methods- DBSCAN, OPTICS, Grid Based Methods- STING, CLIQUE, Model Based Method โ€“Statistical Approach, Neural Network approach, Outlier Analysis.

UNIT III

Concept Description:- Definition, Data Generalization, Analytical Characterization, Analysis of attribute relevance, Mining Class comparisons, Statistical measures in large Databases. Measuring Central Tendency, Measuring Dispersion of Data, Graph Dis-plays of Basic Statistical class Description, Mining Association Rules in Large Databases, Association rule mining, mining Single-Dimensional Boolean Association rules from Transactional Databasesโ€“ Apriori Algorithm, Mining Multilevel Association rules from Transaction Databases & Mining Multi-Dimensional Association rules from Relational Databases.

UNIT IV Overview, Motivation (for Data Mining), Data Mining -Definition; Functionalities, Data Processing, Form of Data Pre-processing, Data Cleaning: Missing Values, Noisy Data, (Binning, Clustering, Regression, Computer & Human inspection), Inconsistent Data, Data Integration & Transformation.

Data Reduction: -Data Cube Aggregation, Dimensionality reduction, Data 35 Compression, Numerosity Reduction, Clustering, Discretization & Concept hierarchy generation.

UNIT V

Aggregation, Historical information, Query Facility, OLAP function & Tools. OLAP Servers, ROLAP, MOLAP, HOLAP, Data Mining interface, Security, Backup & Recovery, Tuning Data Warehouse, Testing Data Warehouse.

Booksโ€‹

  1. Jiawei Han, Micheline Kamber, โ€Data Mining Concepts & Techniquesโ€ Elsevier.
  2. Mallach,โ€Data Warehousing Systemโ€,McGraw โ€“Hill.

6. Software Engineeringโ€‹

UNITโ€“I: SOFTWARE PROCESS AND AGILE DEVELOPMENT

Introduction to Software Engineering - Software Process - Perspective Process Models - Waterfall model - Incremental Process model - RAD Model & Spiral model - Specialized Process Models Software Crisis - Software Myths - Introduction to Agility : Agile process - Extreme programming - XP Process. [REFERENCE-1]

UNITโ€“II: REQUIREMENTS ANALYSIS

Software Requirements: Functional & Non-Functional, User requirements, System requirements - Software Requirements Document - IEEE Standards for SRS - Requirement Engineering Process: Feasibility Studies, Requirements elicitation - Requirements analysis modeling techniques - requirements validation. [BOOK-2 & BOOK-3]

UNITโ€“III: DESIGN

Design process -Design Concepts-Design Modelโ€“ Design Heuristic - Architectural Design -Architectural styles, Architectural Design, Architectural Mapping using Data Flow- User Interface Design: Interface analysis, Interface Design - Component level Design: Designing Class based components, traditional Components. [BOOK-1]

UNITโ€“IV: MODELING AND RISK MANAGEMENT

Unified Modeling Language - principles of modeling - Basic Behavioral Modeling: Use Case - Class Diagram - Activity Diagram - Risk Management: Reactive vs. Proactive Risk strategies, software Risks, Risk identification, Risk projection, Risk Refinement, RMMM, RMMM Plan- Quality Management: Software Quality, Quality concepts, Software quality assurance, Software Reviews, Formal technical reviews.[BOOK-1 & BOOK-2]

UNITโ€“V: TESTING AND MAINTENANCE Software testing fundamentals - Testing Strategies: White box testing โ€“ control structure testing, black box testing - Unit Testing, Integration Testing, Acceptance Testing, Performance Testing - Regression Testing, Validation Testing, System Testing & Debugging - Refactoring - Reverse & Forward Engineering. [BOOK-1]

Booksโ€‹

  1. R.S. Pressman, โ€œSoftware Engineering - A Practitionerโ€™s Approachโ€, Eighth Edition, McGraw Hill International Edition, 2015.
  2. Rajib Mall, โ€Fundamentals of Software Engineeringโ€, 5th Edition, PHI Learning Pvt. Ltd., 2018.
  3. Ian Sommerville, โ€œSoftware Engineeringโ€, Pearson Education

Semester IIIโ€‹

1. Big Data Analyticsโ€‹

PREREQUISITES: DBMS, DWDM

COURSE OBJECTIVES:

  • To optimize business decisions and create competitive advantage with Big Data Analytics
  • To explore the fundamental concepts of big data analytics.
  • To understand the various search methods and visualization techniques.
  • To learn to use various techniques for mining data stream and to understand the applications using Map Reduce Concepts.
  • To introduce programming tools PIG & HIVE in Hadoop echo system.

COURSE OUTCOMES: Students will be able to:

  • Work with big data platform and explore the big data analytics techniques business applications.
  • Design efficient algorithms for mining the data from large volumes.
  • Analyze the HADOOP and Map Reduce technologies associated with big data analytics.
  • Explore on Big Data applications Using Pig and Hive.
  • Understand the fundamentals of various big data analytics techniques and build a complete business data analytics solution.

UNIT-I: INTRODUCTION TO BIG DATA AND ANALYTICS

Classification of Digital Data, Structured and Unstructured Data โ€“Introduction to Big Data: Characteristics โ€“ Evolution โ€“ Definition - Challenges with Big Data- Other Characteristics of Data - Why Big Data - Traditional Business Intelligence versus Big Data - Data Warehouse and Hadoop Environment Big Data Analytics: Classification of Analytics โ€“ Challenges - Big Data Analytics important - Data Science - Data Scientist - Terminologies used in Big Data Environments - Basically Available Soft State Eventual Consistency - Top Analytics Tools

UNIT-II: INTRODUCTION TO TECHNOLOGY LANDSCAPE

NoSQL, Comparison of SQL and NoSQL, Hadoop -RDBMS Versus Hadoop โ€“ Distributed Computing Challenges โ€“ Hadoop Overview - Hadoop Distributed File System โ€“ Processing Data with Hadoop - Managing Resources and Applications with Hadoop YARN -Interacting with Hadoop Ecosystem

UNIT-III: INTRODUCTION TO MONGODB AND MAPREDUCE PROGRAMMING

MongoDB: Why Mongo DB - Terms used in RDBMS and Mongo DB - Data Types -MongoDB Query Language Map Reduce: Mapper โ€“ Reducer โ€“ Combiner โ€“ Partitioner โ€“ Searching โ€“ Sorting โ€“ Compression

UNIT-IV: INTRODUCTION TO HIVE AND PIG

Hive: Introduction โ€“ Architecture - Data Types - File Formats - Hive Query Language Statements โ€“ Partitions โ€“ Bucketing โ€“ Views - Sub- Query โ€“ Joins โ€“ Aggregations - Group by and Having - RCFile Implementation - Hive User Defined Function - Serialization and Deserialization. FRAMEWORKS: Applications on Big Data Using Pig and Hive โ€“ Data processing operators in Pig โ€“ Hive services โ€“ HiveQL โ€“ Querying Data in Hive - fundamentals of HBase and Zoo Keeper - IBM Info Sphere Big Insights and Streams.

UNIT -V: INTRODUCTION TO DATA ANALYTICS WITH R

Machine Learning: Introduction, Supervised Learning, Unsupervised Learning, Machine Learning Algorithms: Regression Model, Clustering, Collaborative Filtering, Associate Rule Making, Decision Tree, Big Data Analytics with BigR. PREDICTIVE ANALYTICS: Simple linear regression-Multiple linear regression- Interpretation of regression coefficients; Visualizations - Visual data analysis techniques- interaction techniques - Systems and applications.

Booksโ€‹

  1. Seema Acharya, Subhashini Chellappan, โ€œBig Data and Analyticsโ€, Wiley Publications, First Edition.
  2. Judith Huruwitz, Alan Nugent, Fern Halper, Marcia Kaufman, โ€œBig data fordummiesโ€, John Wiley & Sons, Inc.(2013)
  3. Tom White, โ€œHadoop The Definitive Guideโ€, Oโ€™Reilly Publications, FourthEdition,2015
  4. Dirk Deroos, Paul C.Zikopoulos, Roman B.Melnky, Bruce Brown, Rafael Coss,โ€œHadoop For Dummiesโ€, Wiley Publications,2014
  5. Robert D.Schneider, โ€œHadoop For Dummiesโ€, John Wiley & Sons, Inc.(2012)

2. Reinforcement Learningโ€‹

PREREQUISITES: Machine Learning, Deep Learning

COURSE OBJECTIVES:

  • Understand the fundamental concepts and principles of bandit algorithms, reinforcement learning (RL), and Markov Decision Processes (MDPs).
  • Explore and analyze different bandit algorithms, including Upper Confidence Bound (UCB), Probably Approximately Correct (PAC), Median Elimination, and Policy Gradient.
  • Gain knowledge of advanced RL techniques such as Dynamic Programming, Temporal Difference (TD) methods, and Bellman Optimality equation.
  • Develop an understanding of eligibility traces, function approximation, and least squares methods in RL.
  • Learn and apply advanced RL techniques including Fitted Q-learning, Deep Q-Network (DQN), and Policy Gradient algorithms for full RL.

COURSE OUTCOMES: Students will be able to:

  • Ability to explain the key concepts and principles of bandit algorithms, RL, and MDPs.
  • Proficiency in implementing and utilizing various bandit algorithms, including UCB, PAC, Median Elimination, and Policy Gradient.
  • Competence in formulating RL problems as MDPs and applying dynamic programming and TD methods to solve them.
  • Skill in utilizing eligibility traces, function approximation, and least squares methods for RL tasks.
  • Proficient in applying advanced RL techniques such as Fitted Q-learning, DQN, and Policy Gradient algorithms to solve complex RL problems and make informed decisions.

UNIT-I: Introduction to Bandit Algorithms

Overview of bandit algorithms, Introduction to Upper Confidence Bound (UCB) algorithm, Introduction to Probably Approximately Correct (PAC) algorithm

UNIT-II: Advanced Bandit Algorithms

Median Elimination algorithm for bandit problems, Policy Gradient algorithm for bandit problems

UNIT-III: Full RL and MDPs

Introduction to full Reinforcement Learning (RL) framework, Markov Decision Processes (MDPs) in RL

UNIT-IV: Dynamic Programming, TD Methods, and Bellman Optimality:

Dynamic Programming methods for solving RL problems, Temporal Difference (TD) methods for RL, Bellman Optimality equation in RL

UNIT -V: Advanced RL Techniques

Eligibility Traces in RL, Function Approximation in RL, Least Squares Methods for RL, Fitted Q-learning, Deep Q-Network (DQN), and Policy Gradient algorithms for full RL

Booksโ€‹

  1. "Bandit Algorithms for Website Optimization" by John Myles White (Publisher: O'Reilly Media), 2020.
  2. "Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew G. Barto (Publisher: The MIT Press), 1998.
  3. "Deep Reinforcement Learning" by Sergey Levine, Pieter Abbeel, and Wojciech Zaremba (Publisher: Springer), 2021.
  4. "Reinforcement Learning: State-of-the-Art" edited by Marco Wiering and Martijn van Otterlo (Publisher: Springer), 2022.
  5. "Fundamentals of Reinforcement Learning" by Charles W. Anderson (Publisher: Morgan & Claypool Publishers), 2020.