MDA107 Advanced Big Data and Text Analytics PDF

School: SSBSR Batch: 2022-24 Program: M.Sc. Academic Year: 2022-23 Branch: Data Semester: II Science & Analytics 1 Course Code MDA107 2 Course Title Advanced Big Data and Text Analytics 3 Credits 4 4 Contact Hours 4-0-0 (L-T-P)...

School: SSBSR Batch: 2022-24 Program: M.Sc. Academic Year: 2022-23 Branch: Data Semester: II Science & Analytics 1 Course Code MDA107 2 Course Title Advanced Big Data and Text Analytics 3 Credits 4 4 Contact Hours 4-0-0 (L-T-P) Course Status Compulsory 5 Course This course aims to provide an insight into the concepts of Natural Language Objective Processing and its applications. This course helps the students to implement NLP applications using deep learning algorithms. This course helps to understand various word/text representation algorithms. 6 Course At the end of the course, the student should be able to Outcomes CO1: Learn about Big data techniques and their applications. CO2: Analyse various neural network problem. CO3: Use different word/text representation methods to see how words are related to each other. CO4: Model different NLP applications using Machine Learning/Deep learning algorithms CO5: Implement different deep learning models to solve real-time NLP problems CO6: Provide a body of concepts and techniques for designing intelligent systems. 7 Course A PG-level course in Soft Computing Techniques to Improve Big Data Analysis Description solutions is to strengthen the dialogue between the statistics and soft computing research communities. 8 Outline syllabus CO Mappi ng Unit 1 A Introduction to Big Data: Introduction to Big Data, CO1 Big Data characteristics, B Types of Big Data, CO1 Structured Data, unstructured Data and semi Structured Data. C Traditional vs. Big Data business approach, CO1 Case Study of Big Data Solutions. Unit 2 A Mining Data Streams:The Stream Data Model: A Data‐Stream‐ CO2 Management System, Examples of Stream Sources, Stream Queries, Issue s in Stream Processing. B Sampling Data in a Stream: Obtaining a Representative Sample, The Gen CO2 eral Sampling Problem, Varying the Sample Size. Filtering Streams: The Bloom Filter, Analysis. C Counting Distinct Elements in a Stream The Count‐ CO2 Distinct Problem, The Flajolet‐Martin Algorithm, Combining Estimates, Space Requirements Counting Ones in a Window: The Cost o f Exact Counts, The Unit 3 A Big Data Analytics and Big Data Analytics Techniques: Big Data and it CO3 s Importance, Drivers for Big data, Optimization techniques, Dimensionality Reduction techniques, B Time series Forecasting, Social Media Mining CO3 and Social Network Analysis and its Application, C Big Data analysis using Hadoop, Pig, CO3 Hive, Mongodb, Spark and Mahout, Data analysis techniques like Di scriminant Analysis and Cluster Analysis, Unit 4 A Introduction to Natural Language Processing-Words-Regular Expressions- CO4 N-grams -Language modelling-Part-of-Speech B Tagging-Named Entity Recognition-Syntactic and Semantic Parsing- CO4 Morphological Analysis C Text Representation and Transformation-Vector space models -Bag-of- CO4 Words-Term Frequency-Inverse Document Frequency-Word Vector representations: Word2vec, GloVe, FastText, BERT-Topic Modelling Unit 5 A Neural language models - Recurrent Neural Network - Long Short-Term CO5 Memory Networks B Encoderdecoder architecture - Attention mechanism - Transformer CO6 networks C Text classification-Sentiment Analysis -Neural Machine Translation - CO6 Question answering - Text summarization Mode of Theory examination Weightage CA MTE ETE Distribution 25% 25% 50% Text book/s* 1. S.N. Sivanandam& S.N. Deepa, Principles of Soft Computing, Wiley Publications, 2nd Edition, 2011. 2.S, Rajasekaran& G.A. VijayalakshmiPai, Neural Networks, 3. Fuzzy Logic & Genetic Algorithms, Synthesis & applications, PHI Publication, 1st Edition, 2009. Other 1.N. K. Bose, Ping Liang, Neural Network fundamental with Graph, References Algorithms & Applications, TMH, 1st Edition, 1998. 2.Rich E, Knight K, Artificial Intelligence, TMH, 3rd Edition, 2012. 3.Martin T Hagen, Neural Network Design, Nelson Candad, 2nd Edition, 2008.