AD3501 DEEP LEARNING LTPG 3003 COURSE OBJECTIVES: + To understand and need and principles of deep neural networks « To understand CNN and RNN architectures of deep neural networks + To comprehend advanced deep learning models + Tolearn the evaluation metrics for deep learning models. UNITI DEEP NETWORKS BASICS 9 Linear Algebra: Scalars — Vectors — Matrices and tensors; Probability Distributions — Gradient. based Optimization - Machine Leaming Basics: Capacity — Qverfitting and underfitting — Hyperparamaters and validation sets — Estimators — Bias and variance — Stochastic gradient descent — Challenges motivating deep learning; Deep Networks: Deep feedforward networks; Regularization — Optimization. UNIT I CONVOLUTIONAL NEURAL NETWORKS 9 Convolution Operation — Sparse Interactions — Parameter Sharing — Equivariance — Pooling — Convolution Variants: Strided — Tiled — Transposed and dilated convolutions; CNN Leaming: Nonlinearity Functions — Loss Functions — Regularization — Optimizers Gradient Computation. UNIT IIL RECURRENT NEURAL NETWORKS 10 Unfolding Graphs — RNN Design Pattems: Acceptor — Encoder --Transducer; Gradient ‘Computation - Sequence Modeling Conditioned on Contexts — Bidirectional RN — Sequence to Sequence RNN — Deep Recurrent Networks — Recursive Neural Networks — Long Term Dependencies; Leaky Units: Skip connections and dropouts; Gated Architecture: LSTM. Hyperparamater — Grid search — Random search — Debugging strategies. UNIT W AUTOENCODERS AND GENERATIVE MODELS 3 Auloencoders: Undercomplete autcencoders — Regularized autoencaders — Stochastic encoders and decoders — Learning with autoencoders: Deep Generative Models: Variational autoencoders — Generative adversarial networks. TOTAL: 45PERIODS COURSE OUTCOMES: After the completion of this course, students will be able to: CO4:Explain the basics in deep neural networks CO2:Apply Convolution Neural Network for image processing CO3:Apply Recurrent Neural Network and its variants for text analysis (CO4:Apply model evaluation for various applications COS:Apply autoencoders and generative models for suitable applications TEXT BOOK 1. lan Goodfellow, Yoshua Bengio, Aaron Courville, “Deep Learning’, MIT Press, 2016. 2. Andrew Glassner, “Deep Learning: A Visual Approach”, No Starch Press, 2021.cwsss1 DATA AND INFORMATION SECURITY LTPec a003 ‘COURSE OBJECTIVES: «To understand the basics of Information Security * = Ta know the legal, ethical and professional issues in Information Security + To equip the students’ knowledge on digital signature, email security and web security UNIT I INTRODUCTION a History, What is Information Security?, Critical Characteristics of Information, NSTISSC Security Medel, Components of an Information System, Securing the Components, Balancing Security and Access, The SDLC, The Security SDLC UNIT ‘SECURITY INVESTIGATION a Need for Security, Business Needs, Threals, Attacks, Legal, Ethical and Professional Issues - An ‘Overview of Computer Security - Access Control Matrix, PolicySecurity policies, Confidentiality policies, Integrity policies and Hybrid policies UNIT i DIGITAL SIGNATURE AND AUTHENTICATION a Digital Signature and Authentication Schemes: Digital signature-Digital Signature Schemes and ‘their Variants- Digital Signature Standards-Authentication: Overview- Requirements Protocols - UNIT IV E-MAIL AND IP SECURITY a E-mail and IP Security: Electronic mail security: Email Architecture -PGP — Operational Descriptions- Key management- Trust Model- S/MIME_IP Security. Overview- Architecture - ESP, AH Protocols IPSec Modes — Security association - Key management. UNIT W WEB SECURITY 3 Web Security: Requirements- Secure Sockets Layer- Objectives-Layers -SSL secure communication-Protocals - Transport Level Security. Secure Electronic Transaction- Entities DS Verification-SET processing. TOTAL :45 PERIODS: ‘COURSE OUTCOMES: Upon successful completion of this course, students will be able to: (C01: Understand the basics of data and information security CO2:Understand the legal, ethical and professional issues in information security (C03: Understand the various authentication schemes to simulate different applications. CO4:Understand various security practices and system security standards (COS:Understand the Web security protocols for E-Commerce applications: TEXT BOOKS: 1. Michael E Whitman and Herbert J Mattord, “Principles of Information Security, Course Technology, 6th Edition, 2017- 2. Stallings William. Cryptography and Network Security: Principles and Practice, Seventh Edition, Pearson Education, 2017.CS3551 DISTRIBUTED COMPUTING LTec (COURSE OBJECTIVES: «To introduce the computation and communication models of distributed systems * Toillustrate the issues of synchronization and collection of information in distributed systems: UNITI INTRODUCTION 8 Introduction: Definition-Relation ta Computer System Components — Motivation — Messag Passing Systems versus Shared Memory Systems — Primitives for Distributed Communication — ‘Synchronous versus Asynchronous Executions — Design Issues and Challenges: A Model of Distributed Computations: A Distributed Program — A Model of Distributed Executions — Models of ‘Communication Networks — Global State of a Distributed System. UNITE LOGICAL TIME AND GLOBAL STATE 10 Logical Time: Physical Clock Synchronization: NTP — A Framework for a System of Logical Clocks — Scalar Time — Vector Time; Message Ordering and Group Communication: Message Ordering Paradigms — Asynchronous Execution with Synchronous Communication — Synchronous Program ‘Order on Asynchronous System — Group Communication — Gausal Order — Total Order; Giobal ‘State and Snapshot Recording Algorithms: Introduction — System Model and Definitions — ‘Snapshot Algorithms for FIFO Channels. UNIT II DISTRIBUTED MUTEX AND DEADLOCK 10 Distributed Mutual exclusion Algorithms: Introduction — Preliminaries - Lamport’s algorithm — Ricart- Agrawala's Algorithm — Token-Based Algorithms — Suzuki Kasami's Broadcast Algorithm, Deadlock Detection in Distributed Systems: Introduction — System Model — Preliminaries — Models ‘of Deadlocks — Chandy-Misra-Haas Algorithm for the AND madel and OR Model. UNITIV CONSENSUS AND RECOVERY 10 ‘Consensus and Agreement Algorithms: Problem Definition — Overview of Results — Agreement in a Failure-Free System(Synchronous and Asynchronaus) — Agreement in Synchronous Systems with Failures; Checkpointing and Rollback Recovery: Introduction — Background and Definitions — Issues in Failure Recovery — Checkpoint-based Recovery — Coordinated Checkpointing Algorithm - = Algorithm for Asynchronous Checkpointing and Recovery UNIT V CLOUD COMPUTING T Definition of Cloud Computing — Characteristics of Cloud — Cloud Deployment Models — Cloud ‘Service Models — Driving Factors and Challenges of Cloud — Virtualization — Load Balancing — ‘COURSE OUTCOMES: Upon the completion of this course, the student will be able to COM: Explain the foundations of distributed systems (K2) C02: Solve synchronization and state consistency problems (K3) COS Use resource sharing techniques in distributed systems (K3) COd: Apply working model of consensus and reliability of distributed systems (K3) COS: Explain the fundamentals of cloud computing (K2)ccs334 BIG DATA ANALYTICS Ltec 2023 ‘COURSE OBJECTIVES: «© Tounderstand big data. * Toleam and use NoSQL big data management. © To learn mapreduce analytics using Hadoop and related tools. * Towork with map reduce applications * To understand the usage of Hadaop related tools for Big Data Analytics UNITI UNDERSTANDING BIG DATA 5 Introduction te big data — convergence of key trends — unstructured data — industry examples of big data — web analytics — big data applications— big data technologies — introduction to Hadoop — ‘open source technologies — cloud and big data — mobile business intelligence — Crowd sourcing analytics ~ inter and trans firewall analytics. UNIT I NOSQL DATA MANAGEMENT T Introduction to NoSQL - aggregate data models - key-value and document data models — relationships — graph databases — schemaless databases — materialized views — distribution ‘models — master-stave replication — consistency - Cassandra — Cassandra data model — ‘Cassandra examples - Cassandra clients UNIT IV MAP REDUCE APPLICATIONS 6 MapReduce workflows — unit tests with MRUnit — test data and local tests — anatomy of MapReduce job run — classic Map-reduce — YARN - failures in classic Map-reduce and YARN — job scheduling — shutfle and sort — task execution — MapReduce types — input formats — output formats. ‘UNIT IIL BASICS OF HADOOP 6 Data format — analyzing data with Hadoop - scaling out — Hadoop streaming — Hadoop pipes — design of Hadoop distributed file system (HDFS)— HDFS concepts — Java interface — data flow — Hadeop VO — data integrity — compression — serialization - Avro — file-based data structures - (Cassandra — Hadoop integration. ‘UNIT V HADOOP RELATED TOOLS 6 Hbase — data model and implementations — Hbase clients -Hbase examples — praxis. Pig — Grunt — pig data model — Pig Latin — developing and testing Pig Latin scripts. Hive — data types and file formats — HiveQL data definition — HiveQL data manipulation — HiveQL queries. ‘30 PERIODS ‘COURSE OUTCOMES: After the complation of this course, students will be able to: (CO1:Describe big data and use cases from selected business domains. (€02:Explain NoSQL big data management. CO3:Install, configure, and run Hadcop and HDFS. (CO4:Perform map-reduce analytics using Hadaop. (COS:Use Hadoop-related tools such as HBase, Cassandra, Pig, and Hive for big data analytics.ccs349 IMAGE AND VIDEO ANALYTICS LTPC 2023 ‘COURSE OBJECTIVES: « Tounderstand the basics of image processing techniques for computer vision. Ta learn the techniques used for image pre-processing. Ta discuss the various object detection techniques. To understand the various Object recognition mechanisms. To elaborate on the video analytics techniques. UNITI INTRODUCTION 6 Computer Vision — Image representation and image analysis tasks - Image representations — digitization — properties — color images — Data structures for Image Analysis - Levels of image data representation - Traditional and Hierarchical image data structures. UNIT IMAGE PRE-PROCESSING 6 Local pre-processing - Image smoothing - Edge detectors - Zero-crassings of the second derivative - Scale in image processing - Canny edge detection - Parametric edge models - Edges in multi-speralct images - Local pre-processing in the frequency domain - Line detection by local pre-processing operators - Image restoration. UNIT I OBJECT DETECTION USING MACHINE LEARNING 6 Object detection— Object detection methods — Deep Learning framework for Object detection— bounding box approach-Intersection over Union (lol) —Deep Learning Architectures-R-CNN-Faster R-CNN-You Only Look Once(YOLO}-Salient features-Loss Functions-YOLO architectures UNIT IV FACE RECOGNITION AND GESTURE RECOGNITION 6 Face Recognition-tntroduction-Applications of Face Recognition Process of Face Recognitian- DeepFace solution by Facebook-FaceNet for Face Recognition. Implementation using FaceNet- Gesture Recognition, UNIT W VIDEO ANALYTICS 6 Video Processing — use cases of video analytics-Vanishing Gradient and exploding gradient problem-ResiNet architecture-RestNet and skip conhectionsnception Network-GoogleNet architecturé-Impravement in Inception v2-Video analytics RestNet and Inception v3. 30 PERIODS LIST OF EXERCISES 30 PERIODS 1. Write a program that computes the T-pyramid of an image. 2. Write a program that derives the quad tree representation of an image using the homogeneity criterion of equal intensity 3. Develop programs for the following gecmatric transforms: (a) Rotation (b) Change of scale (c) Skewing (d) Affine transform calculated from thrae pairs of corresponding points (e) Bilinear transform calculated from four pairs of corresponding points. 4. Develop.a program to implement Object Detection and Recognition 5. Develop a program for motion analysis using moving edges, and apply it to your image