MLR Institute of Technology CLOUD COMPUTING (PROFESSIONAL ELECTIVE - Ill) IVB. TECH- | SEMESTER Course Code Category Hours /Week | Credits) Maximum Marks Lit] Pp c cE | SEE | Total ASCS23 PEC 3] -] - 3 30 | 70 | 100 COURSE OBJECTIVES 1. Toinculcate the concepts of distributed computing 2 To familiarize the concepts of cloud computing and services 3. To explain cloud platform and types of cloud 4, To explain resource management in cloud COURSE OUTCOMES ‘Analyze the principles of distributed computing 2. Create virtual machines and virtual templates. 3. Create Cloud platform using Virtual machines 4 5. Apply suitable business models of loud computing ‘Analyze various case studies on cloud computing. UNIT. | INTRODUCTION TO VIRTUALIZATION AND TECHNOLOGIES CLASSES: 12 INTRODUCTION TO VIRTUALIZATION AND TECHNOLOGIES: Introduction to Virtualization: Definition, Objectives, Characteristics, Benefits of virtualization, Taxonomy of virtualization technologies, Pros and cons of virtualization. Virtualization Technologies: VMware, Hyper-V, Zen and virtual iron. UNIT | FUNDAMENTAL CLOUD COMPUTING AND MODELS CLASSES: 12 FUNDAMENTAL CLOUD COMPUTING AND MODELS: Cloud Computing: Origin and influences, Basic concepts and terminology, Goals and benefits, Risks and challenges. Cloud Models, roles and boundaries, Cloud characteristics, Cloud delivery models, Cloud deployment models, UNIT-II_ | CLOUD COMPUTING MECHANISMS AND ARCHITECTURE CLASSES: 14 CLOUD COMPUTING MECHANISMS AND ARCHITECTURE: Cloud-Enabling Technology: Broadband networks and internet architecture, Data center technology, Virtualization technology, Web technology, Muttitenant technology, Service technology. Cloud Architectures: Architecture - Workload distribution, Resource pooling, Dynamic scalability, Elastic resource capacity, Service load balancing, Cloud bursting, Elastic disk provisioning, Redundant storage. UNIT-IV_ | CLOUD SECURITY AND DISASTER RECOVERY CLASSES: 12 CLOUD SECURITY AND DISASTER RECOVERY: Cloud Security: Data, Network and host security, Cloud security services and cloud security possible solutions. Cloud Disaster Recovery: Disaster recovery planning, Disasters in the cloud, Disaster management, Capacity planning and cloud scale. uNit-v_ | CLouD CASE STUDIES CLASSES: 10 CLOUD CASE STUDIES: Case Studies: Software-as-a-Service (SaaS) - Salesforce.com, Facebook; Platform-as-a-Service (PaaS) - Google App Engine, MS-Azure and IBM Bluemix; Infrastructure-as-a- ‘Service (laa) - Amazon EC2, Amazon $3 and Nettlix. TEXT BOOKS Bi Tech- Computer Sclence and Eneineerine . MLE? Pace 1127MLR Institute of Technology 1. Cloud ComputingConcepts, Technology and Architecture, Thomas Ef and RicardoPuttini Pearson, 2013 2 Cloud Computing Virtualization Specialist Complete Certification Kit-Study Guide Book, Ivanka Menken and Gerard Blokdlik, Lightning Source, 2009, REFERENCE BOOKS 7, _ Cloud Computing Bible, Barrie Sosinsky, Wiley India Pvt Ltd, 2077 2 Cloud Computing Principles and Paradigms, Rajkumar Buyya, James Broberg and Andrzej Goscinski, John Wiley and Sons, 2011, 3, Cloud Computing Implementation, John W. Rittinghouse and James F. Ransome, Management and Security, CRC Press, Taylor & Francis Group, 2010. WEB LINKS 1. hitps//onlinecourses.nptel.ac.in/noc?1_cs14/preview 2, _https:/www.ibm,com/in-en/cloud/leam/cloud-computing Bi Tech- Computer Sclence and Eneineerine . MLE? Pace 1128MLR Institute of Technology SOFT COMPUTING (PROFESSIONAL ELECTIVE - Il) IVB. TECH- | SEMESTER Course Code Category Hours /Week | Credits) Maximum Marks. L| Tt] P c CIE | SEE] Total ASITI9 PEC 3] -] - 3 30 | 70 | 100 COURSE OBJECTIVE 1. To teach basic neural networks, fuzzy systems, and optimization algorithms concepts and their relations 2. To provide knowledge of Neuron model, and Applications of NN to discuss their work 3. To provide the graduate the better understanding of Fuzzy Logic and Evolutionary Computations COURSE OUTCOMES 1. Tolearn neural network (NN) paradigms 2. Apply different supervised learning algorithms on given data 3, Analyze feedback neural networks &self organizing feature map 4, To leam fuzzy logic To have a knowledge of evolutionary computations, genetic algorithm(GA), evolutionary programming, classifier systems, genetic programming parse trees, mathematical foundation of GA variants of GA 5.__ Apply different genetic algorithms on given data UNIT4 | BASICS OF ARTIFICIAL NEURAL NETWORK CLASSE: 4 BASICS OF ARTIFICIAL NEURAL NETWORK: Characteristics of Neural Networks, Structure and working of a biologicalneural network, Aificial neural network: terminology, models of neurons: McCulloch Pitts model, Perceptron model, Adaline model, topology, Basic learning laws. FUNCTIONAL UNITS FOR ANN FOR PATTERN RECOGNITION TASK: Patter recognition problem, Basic functionalunits, PR by functional units, UNIT«I | FEEDFORWARD NEURAL NETWORKS CLASSES: 12 FEEDFORWARD NEURAL NETWORKS: ‘SUPERVISED LEARNING - I: Perceptrons - Learning and memory, Learning algorithms, Error correction and gradientdecent rules, Perceptron learning algorithms. SUPERVISED LEARNING4I: Back propagation, Multilayered network architectures, Back propagation leamingalgorithm, Example applications of feed forward neural networks unrrany_ | FEEDBACK NEURAL NETWORKS & SELF ORGANIZING FEATURE | 1 asses. 14 FEEDBACK NEURAL NETWORKS & SELF ORGANIZING FEATURE MAP: Introduction, Associative leaming, Hopfieldnetwork, Error performance in Hopfield networks, simulated annealing, Boltzmann machine and Boltzmann learning, state transition diagram and false minima problem, stochastic update, simulated annealing, Boltzmann machine, bidirectional associative memory, bam stability analysis. Self ‘organization, generalized learning laws, compatitive learning, vector quantization, self organizing feature map, applications of self organizing feature map. uNitv | Fuzzy Locic CLASSES: 10 FUZZY LOGIG: Fuzzy set theory, crisp sets, operations on crisp sel, fuzzy sels, fuzzy versus crisp, ‘operations, fuzzyrelations, crisp relations, properties. Fuzzy logic Application: Fuzzy Control of Blood Pressure, UNIT-V_| FUZZY LOGIC IN DATABASE AND INFORMATION SYSTEMS, CLASSE: Bi Tech- Computer Sclence and Eneineerine . MLE? Pace 1120MLR Institute of Technology FUZZY LOGIC IN DATABASE AND INFORMATION SYSTEMS: Fuzzy Informalion, Fuzzy Logic in database Systems, FuzzyRelational data Models, operations in Fuzzy Relational data Models, Design theory for Fuzzy Relational databases, Fuzzy information Retrieval and Web search, Fuzzy Object Oriented databases, GENETIC ALGORITHMS: Introduction to Genetic Algorithms, Evolutionary Algorithms. TEXT BOOKS 1. Neural Networks A classroom Approach, Satish Kumar (2004), Tata McGraw Hill Publication, New Delhi, 2. Soft computing and Fuzzy Logic, Lotfi A. Zadeh(1997), World Scientific Publishing Co., Inc. River Edge, NJ, USA, REFERENCE BOOKS 1. Atiificial Neural Networks, B. Yegnanarayana (2006), Prentice Hall of India, New Delhi, India 2, Fuzzy Logic, John Yen, Reza Langari(2006), Pearson Education, New Delhi, India 3, Neural networks, Fuzzy Logic and Genetic Algorithms Synthesis andApplications, S. Rajasekaran, Vijaylakshmi Pari (2003), Prentice Hall of India, New Delhi, India, WEB LINKS 1. hitps:iwww javatpoint, com/what-is-soft-computing 2. hittps:/inptel.ac.in/courses/106/105/106105173/ Bi Tech- Computer Sclence and Eneineerine . MLE? Race 1140MLR Institute of Technology NATURAL LANGUAGE PROCESSING (PROFESSIONAL ELECTIVE - Ill) - B. TECH- ISEMESTER Course Code Category Hours / Week | Credits Maximum Marks Lot) P| ¢ ) ce SEE Total ASAIOS PEC poo ooo a)-| - 3 30 70 100 COURSE OBJECTIVES To learn unstructured data 1. Introduce to some of Problems and Solutions of NLP and thelr Relation to linguistics and statics. 2. Understands, Generates and manipulates Human Language COURSE OUTCOMES Upon successful completion of the course, the student is able to 4. Show sensitivity Linguistic phenomena and an ability to model them with formal grammars 2. Apply proper experimental methodology for training and evaluating empirical NLP systems. 3. Able to manipulate probabilities, Construct statistical models over strings and trees and estimate parameters using supervised and unsupervised training methods. 4, To Design, Implement and Analyze NLP algorithms. 5,__ To Design different language modeling Techniques. UNIT | FINDING THE STRUCTURE OF WORDS CLASSES: 12 FINDING THE STRUCTURE OF WORDS : Words and Their components, Issues and Challenges FINDING THE STRUCTURE OF DOCUMENTS: Introduction, Methods ,complexity of the Approaches, Performance of Approaches UNIT SYNTAX ANALYSIS CLASSES: 12 ‘SYNTAX ANALYSIS:Parsing Natural Language , Tree banks : A Data-Driven Approach to syntax, Representation of Syntactic Structure, Parsing algorithms Models for Ambiguity Resolution in Parsing, Multilingual Issues UNIT-I|_ SEMANTIC PARSING CLASSES: 12 ‘SEMANTIC PARSING: Introduction, Semantic interpretation, System paradigms, Word Sense Systems Software UNITAV_ PREDICATE ARGUMENT STRUCTURE CLASSES: 19 PREDICATE ARGUMENT STRUCTURE:Predicate Argument Structure, Meaning Representation systems, Software. UNIT-V__ DISCOURSE PROCESSING & LANGUAGE MODELING CLASSES: 14 DISCOURSE PROCESSING: Cohesion Reference Resolution, Discourse Cohesion and structure LLANGUAGE MODELING: Introduction, N-Gram Models, Language model Evaluation, Parameter Estimation, Language Model Adaptation ,Types of Language Models, Language Specific Modeling Problems, Multilingual and Cross Lingual Language Modeling TEXT BOOKS Bi Tech- Computer Sclence and Eneineerine . MLM? Dare |141tute of Technology 1. Multilingual natural Language processing Applications : From Theory to Practice-Daniel M. Bike! and Imedzitouni Pearson Publication, 2. Natural Language Processing and Information Retrieval -TanvierSiddiqui,U.S.Tiwary REFERENCE BOOKS 1. Speech And Natural Language Processing-Daniel Jurafsky&James H Martin, Pearson Publication, WEB LINKS 41. hltps://onlinecourses.nptel.ac.ininoc19_cs56/preview Bi Tech- Computer Sclence and Eneineerine . MLE? Race 1142