0% found this document useful (0 votes)
8 views24 pages

06-01syllabus 6thsem

The document outlines the syllabi for core courses in Artificial Intelligence, Robotics, and Image Processing for B. Tech VI Semester students admitted in 2022-23. It details course objectives, units of study, recommended books, and expected outcomes for each course, including AI for Robotics, Image Processing, and AI & Machine Learning. The document emphasizes the integration of AI techniques in robotics and image processing, along with practical applications and advanced methodologies.

Uploaded by

luciferg185
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
8 views24 pages

06-01syllabus 6thsem

The document outlines the syllabi for core courses in Artificial Intelligence, Robotics, and Image Processing for B. Tech VI Semester students admitted in 2022-23. It details course objectives, units of study, recommended books, and expected outcomes for each course, including AI for Robotics, Image Processing, and AI & Machine Learning. The document emphasizes the integration of AI techniques in robotics and image processing, along with practical applications and advanced methodologies.

Uploaded by

luciferg185
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 24

‭Centre for Artificial Intelligence‬

‭Syllabi‬
‭of‬
‭Departmental Core Courses (DC)‬
‭of‬
‭B. Tech VI Semester‬
‭[Information Technology (Artificial Intelligence and‬
‭Robotics)/ Artificial Intelligence (AI) and Data Science/‬
‭Artificial Intelligence (AI) and Machine Learning]‬
‭for batch admitted in 2022-23‬
‭(under the flexible curriculum)‬
‭Centre for Artificial Intelligence‬
‭AI FOR ROBOTICS‬
‭(2240621)‬

‭COURSE OBJECTIVES‬

‭●‬ ‭To study the concepts of Artificial Intelligence in Robotics.‬


‭●‬ ‭To learn the methods of solving problems in Robotics using Artificial Intelligence.‬
‭●‬ ‭To learn about planning, strategies and algorithms.‬

‭Unit I‬
‭Introduction‬ ‭to‬ ‭Robotics‬ ‭Engineering‬ ‭and‬ ‭AI‬ ‭Integration‬‭:‬ ‭Overview‬ ‭of‬ ‭Robotics‬ ‭Engineering,‬
‭Laws‬ ‭of‬ ‭Robotics,‬ ‭Types‬ ‭of‬ ‭Robot,‬ ‭Components‬ ‭Needed‬ ‭for‬ ‭Robot,‬ ‭Robot‬ ‭Standards‬ ‭and‬ ‭Safety‬
‭Regulations,‬ ‭Robot‬ ‭System‬ ‭Analysis,‬ ‭Trends‬ ‭in‬ ‭Robotics‬ ‭System,‬ ‭Requirements‬ ‭of‬ ‭AI‬ ‭for‬ ‭Robot‬
‭Automation, AI agents, Algorithms used in Robotics, Case Studies: Sofia, ASIMO, IBM Watson.‬

‭Unit II‬
‭Path‬ ‭Planning‬ ‭and‬ ‭Control‬ ‭in‬ ‭Robotics:‬‭Overview‬‭of‬‭Path‬‭Planning‬‭and‬‭Control,‬‭Path‬‭Planning‬
‭Categories:‬ ‭Environment-based,‬ ‭Algorithm-based,‬ ‭Completeness-based,‬ ‭Robot‬ ‭Control‬
‭Architectures for Path Following, Robot Path Planning Problem, and Complexity.‬

‭Unit III‬
‭Artificial‬ ‭Intelligence‬ ‭for‬ ‭Global‬ ‭Path‬ ‭Planning:‬ ‭Classical‬‭Approaches‬‭to‬‭Path‬‭Planning,‬‭Graph‬
‭Search‬ ‭Approaches:‬ ‭A*‬ ‭and‬ ‭AO*‬ ‭Algorithm,‬ ‭Heuristic‬ ‭Approaches:‬ ‭Tabu‬ ‭Search,‬ ‭Genetic‬
‭Algorithm,‬ ‭Ant‬ ‭Colony‬ ‭Optimization,‬ ‭Hybrid‬ ‭Approaches‬ ‭in‬ ‭Path‬ ‭Planning,‬ ‭Case‬ ‭studies‬ ‭of‬
‭AI-powered Path Planning in Robotics.‬

‭Unit IV‬
‭Simultaneous‬ ‭Localization‬ ‭and‬ ‭Mapping‬ ‭(SLAM):‬ ‭Introduction‬ ‭to‬ ‭SLAM,‬ ‭EKF-SLAM,‬
‭Graph-based‬ ‭SLAM‬ ‭(G-SLAM),‬ ‭Feature-based‬ ‭Mapping:‬ ‭Feature‬ ‭extraction‬ ‭and‬ ‭matching,‬
‭FastSLAM algorithm, Comparison of feature-based mapping techniques.‬

‭Unit V‬
‭Advancements in AI for Robotics:‬‭Swarm Robotics and‬‭Multi-Robot Systems, Bio-inspired‬
‭Robotics, Integration of AI and Robotics in Industry 4.0.‬
‭Centre for Artificial Intelligence‬
‭RECOMMENDED BOOKS‬

‭1.‬ ‭Poole, Harry H. “Fundamentals of robotics engineering. Springer Science & Business Media”, 2012.‬
‭2.‬ ‭Steven M. LaValle, “Planning Algorithms”, 2006.‬
‭3.‬ ‭Anis‬ ‭Koubaa,‬ ‭Hachemi‬ ‭Bennaceur,‬ ‭Imen‬ ‭Chaari,‬ ‭Sahar‬‭Trigui,‬‭Adel‬‭Ammar,‬‭Mohamed-Foued‬‭Sriti,‬
‭Maram‬ ‭Alajlan,‬ ‭Omar‬ ‭Cheikhrouhou,‬ ‭Yasir‬ ‭Javed,‬ ‭“Path‬ ‭Planning‬ ‭and‬ ‭Cooperation:‬ ‭Foundations,‬
‭Algorithms and Experimentations”, 2018.‬
‭4.‬ ‭Robin R. Murphy, “Introduction to AI Robotics”, second edition, 2019.‬
‭5.‬ ‭Dubey,‬‭Ashutosh‬‭Kumar,‬‭Abhishek‬‭Kumar,‬‭S.‬‭Rakesh‬‭Kumar,‬‭N.‬‭Gayathri,‬‭and‬‭Prasenjit‬‭Das,‬‭eds.‬‭AI‬
‭and IoT-based Intelligent Automation in Robotics. John Wiley & Sons, 2021.‬

‭COURSE OUTCOMES‬

‭After completion of this course, the students would be able to:‬

‭CO1.‬ ‭describe‬ ‭fundamental‬ ‭concepts‬ ‭in‬ ‭robotics‬ ‭engineering‬ ‭and‬ ‭Artificial‬ ‭Intelligence‬ ‭integration‬ ‭in‬
‭robotics.‬
‭CO2. explain the basics of robotics path planning and control.‬
‭CO3.‬ ‭utilize‬ ‭various‬ ‭artificial‬ ‭intelligence‬ ‭techniques‬ ‭for‬ ‭effective‬ ‭global‬ ‭path‬ ‭planning‬ ‭solutions‬ ‭in‬
‭diverse robotic scenarios.‬
‭CO4. discover appropriate Simultaneous Localization and Mapping techniques for robots.‬
‭CO5.‬ ‭evaluate‬ ‭the‬ ‭strengths,‬ ‭weaknesses,‬ ‭and‬ ‭trade-offs‬‭among‬‭various‬‭Simultaneous‬‭Localization‬‭and‬
‭Mapping methods.‬
‭CO6.‬‭design‬‭and‬‭propose‬‭advanced‬‭solutions‬‭for‬‭addressing‬‭complex‬‭challenges‬‭in‬‭the‬‭field‬‭of‬‭Artificial‬
‭Intelligence for robotics.‬
‭CO-PO Mapping Matrix‬
‭PO1‬ ‭PO2‬ ‭PO3‬ ‭PO4‬ ‭PO5‬ ‭PO6‬ ‭PO7‬ ‭PO8‬ ‭PO9‬ ‭PO10‬ ‭PO11‬ ‭PO12‬ ‭PSO1‬ ‭PSO2‬
‭CO1‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭3‬ ‭2‬
‭CO2‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭2‬ ‭1‬ ‭3‬ ‭2‬
‭CO3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭2‬ ‭3‬ ‭1‬
‭CO4‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭3‬ ‭1‬
‭CO5‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭3‬ ‭2‬
‭CO6‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬
‭Centre for Artificial Intelligence‬
I‭ MAGE PROCESSING‬
‭(2240622/2270622/2280622)‬

‭COURSE OBJECTIVES‬
‭●‬ ‭To impart knowledge about the fundamental steps of image processing.‬
‭●‬ ‭To study the various image enhancement and segmentation techniques in spatial and frequency‬
‭domain‬
‭●‬ ‭To understand image compression, image segmentation and Color image processing.‬

‭Unit I‬
‭Introduction:‬ ‭Digital‬ ‭image‬ ‭representation,‬ ‭Fundamental‬ ‭steps‬ ‭in‬ ‭image‬ ‭processing,‬ ‭Components‬ ‭of‬
‭Digital‬ ‭Image‬ ‭processing‬ ‭systems,‬ ‭Elements‬ ‭of‬ ‭visual‬ ‭perception,‬ ‭Image‬ ‭Formation‬ ‭model,‬ ‭Image‬
‭Sampling‬ ‭and‬ ‭quantization,‬ ‭Relationship‬ ‭between‬ ‭pixels‬ ‭–‬ ‭neighbourhood,‬ ‭adjacency‬ ‭connectivity,‬
‭regions, boundaries and distance measures.‬
‭Unit II‬
‭Image‬ ‭Enhancement:‬ ‭Enhancement‬ ‭by‬ ‭point‬ ‭processing,‬ ‭Sample‬ ‭intensity‬ ‭transformation,‬ ‭Histogram‬
‭processing,‬‭Image‬‭subtraction,‬‭Image‬‭averaging,‬‭Spatial‬‭filtering-‬‭Smoothing‬‭Spatial‬‭filters,‬‭Sharpening‬
‭Spatial filters.‬
‭Unit III‬
‭Image‬ ‭Segmentation:‬ ‭Detection‬ ‭of‬ ‭discontinuities‬ ‭-‬ ‭point,‬ ‭line‬ ‭and‬ ‭edge‬ ‭detection,‬ ‭Edge‬ ‭linking‬ ‭and‬
‭boundary‬ ‭detection,‬ ‭Thresholding,‬ ‭Region‬ ‭based‬ ‭segmentation‬ ‭-‬ ‭region‬ ‭growing,‬ ‭region‬ ‭splitting‬ ‭and‬
‭merging, Use of motion in segmentation- Spatial techniques and Frequency domain techniques.‬
‭Unit IV‬
‭Image‬ ‭Restoration‬ ‭and‬ ‭Compression:‬ ‭A‬ ‭model‬ ‭of‬ ‭the‬ ‭image‬ ‭degradation/restoration‬ ‭process,‬ ‭noise‬
‭models,‬ ‭restoration‬ ‭in‬ ‭the‬ ‭presence‬ ‭of‬ ‭noise–only‬ ‭spatial‬ ‭filtering,‬ ‭Weiner‬ ‭filtering,‬ ‭constrained‬ ‭least‬
‭squares‬‭filtering,‬‭geometric‬‭transforms;‬‭Introduction‬‭to‬‭the‬‭Fourier‬‭transform‬‭and‬‭the‬‭frequency‬‭domain,‬
‭estimating‬ ‭the‬ ‭degradation‬ ‭function.‬ ‭Image‬ ‭Data‬ ‭Compression:‬ ‭Fundamentals,‬ ‭Compression‬ ‭models,‬
‭Error free compression, Lossy Compression, Image compression standards.‬
‭Unit V‬
‭Color‬ ‭Image‬ ‭Processing:‬ ‭Color‬ ‭Models,‬ ‭Pseudo‬ ‭color‬ ‭Image‬ ‭Processing,‬ ‭Color‬ ‭Transformations,‬
‭Smoothing‬ ‭and‬ ‭sharpening,‬ ‭Image‬ ‭Segmentation‬ ‭based‬ ‭on‬ ‭color.‬ ‭Applications‬ ‭of‬ ‭Image‬ ‭Processing:‬
‭Medical imaging, Robot vision, Character recognition, Remote Sensing.‬
‭Centre for Artificial Intelligence‬
‭RECOMMENDED BOOKS‬
‭1.‬ ‭R.‬ ‭C.‬ ‭Gonzalez‬ ‭and‬ ‭R.‬ ‭E.‬ ‭Woods,‬ ‭Digital‬ ‭Image‬ ‭Processing,‬ ‭Addison-Wesley‬ ‭Publishing‬ ‭Company,‬
‭2007‬
‭2.‬ ‭Gonzalez‬‭R.‬‭C,‬‭Woods‬‭R.‬‭E‬‭and‬‭Eddins‬‭S.‬‭L;Digital‬‭Image‬‭Processing‬‭using‬‭MATLAB,‬‭McGraw‬‭Hill‬
‭Education, 2nd edition, 2017.‬
‭3.‬ ‭Sonka‬ ‭M.‬‭Hlavac‬‭V.,‬‭Boyle‬‭R.,‬ ‭Image‬‭Processing,‬‭Analysis‬‭and‬‭Machine‬‭Vision,‬‭Cengage‬‭Learning,‬
‭3rd edition, 2007.‬
‭4.‬ ‭A. K. Jain, Fundamentals of Digital Images Processing, Pearson Education India, 2015‬

‭COURSE OUTCOMES‬
‭After completion of the course students will be able to:‬
‭CO1: describe the fundamentals of image processing.‬
‭CO2: classify image enhancement techniques in both spatial and frequency domains‬
‭CO3: apply image segmentation for object and boundary detection.‬
‭CO4: analyze the causes for image degradation and image restoration.‬
‭CO5: evaluate image compression techniques.‬
‭CO6: implement novel image filtering techniques.‬

‭CO-PO Mapping Matrix‬


‭PO1‬ ‭PO2‬ ‭PO3‬ ‭PO4‬ ‭PO5‬ ‭PO6‬ ‭PO7‬ ‭PO8‬ ‭PO9‬ ‭PO10‬ ‭PO11‬ ‭PO12‬ ‭PSO1‬ ‭PSO2‬
‭CO1‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭3‬ ‭2‬
‭CO2‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭1‬ ‭3‬ ‭2‬
‭CO3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭3‬ ‭1‬ ‭1‬ ‭2‬ ‭3‬ ‭3‬
‭CO4‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭3‬ ‭2‬
‭CO5‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭3‬ ‭2‬
‭CO6‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭2‬ ‭2‬ ‭3‬ ‭2‬ ‭3‬ ‭3‬
‭Centre for Artificial Intelligence‬
‭ARTIFICIAL INTELLIGENCE & MACHINE LEARNING‬
‭(2240623)‬

‭COURSE OBJECTIVES‬
‭●‬ ‭To provide the fundamental knowledge of Artificial Intelligence and Machine Learning.‬
‭●‬ ‭To‬ ‭present‬ ‭the‬ ‭basic‬ ‭representation‬ ‭and‬ ‭reasoning‬ ‭paradigms‬ ‭used‬ ‭in‬ ‭Artificial‬ ‭Intelligence‬ ‭and‬
‭Machine Learning.‬
‭●‬ ‭To understand the working of techniques used in Artificial Intelligence and Machine Learning.‬
‭Unit I‬
‭Introducing‬ ‭Artificial‬ ‭Intelligence:‬ ‭Computation,‬ ‭Psychology‬ ‭and‬ ‭Cognitive‬ ‭Science,‬ ‭Perception,‬
‭Understanding‬‭and‬‭Action.‬‭Artificial‬‭Intelligence‬‭vs‬‭Machine‬‭Learning‬‭vs‬‭Deep‬‭Learning.,‬‭Key‬‭Elements‬
‭of‬ ‭Machine‬ ‭Learning:‬ ‭Representation,‬ ‭Process‬ ‭(Data‬ ‭Collection,‬ ‭Data‬ ‭Preparation,‬ ‭Model‬ ‭Selection,‬
‭Model‬ ‭Training,‬ ‭Model‬‭Evaluation‬‭and‬‭Prediction),‬‭Evaluation‬‭and‬‭Optimization.‬‭Maximum‬‭likelihood‬
‭estimation,‬ ‭Types‬ ‭of‬ ‭Learning:‬ ‭Supervised,‬ ‭Unsupervised‬ ‭and‬ ‭Reinforcement‬ ‭Learning.‬ ‭Regression‬ ‭vs‬
‭Classification Problems Applications of Artificial intelligence and Machine Learning in the real world.‬
‭Unit II‬
‭Problem,‬ ‭Problem‬ ‭Space‬ ‭and‬ ‭Search:‬ ‭Production‬ ‭System,‬ ‭Blind‬ ‭Search:‬ ‭BFS‬ ‭&‬ ‭DFS,‬ ‭Heuristic‬
‭Search, Hill Climbing, Best First Search.‬
‭Introduction‬ ‭to‬ ‭Neural‬ ‭Networks:‬ ‭History,‬ ‭Biological‬ ‭Neuron,‬ ‭Artificial‬ ‭Neural‬ ‭Network,‬ ‭Neural‬
‭Networks‬ ‭Multilayer‬ ‭Perceptron,‬ ‭Back-propagation‬ ‭algorithm‬ ‭and‬ ‭its‬ ‭variants‬ ‭Stochastic‬ ‭gradient‬
‭descent.‬
‭Unit III‬
‭Supervised‬ ‭Machine‬ ‭Learning:‬ ‭Linear‬ ‭Regression:‬ ‭Implementation,‬ ‭Applications‬ ‭&‬ ‭Performance‬
‭Parameters,‬‭K-Nearest‬‭Neighbour‬‭Classification‬‭Decision‬‭Tree‬‭Classifier,‬‭Terminology,‬‭Classification‬‭vs‬
‭Regression‬‭Trees,‬‭Tree‬‭Creation‬‭with‬‭Gini‬‭Index‬‭and‬‭Information‬‭Gain,‬‭IDE3‬‭Algorithms,‬‭Applications‬
‭and‬ ‭Performance‬ ‭Parameters.‬ ‭Random‬ ‭Forest‬ ‭Classifier,‬ ‭Naïve‬ ‭Bayes‬ ‭Classifier,‬ ‭Support‬ ‭Vector‬
‭Machines Case Study on Regression and Classification for solving real world problems.‬
‭Unit IV‬
‭Unsupervised‬ ‭Machine‬ ‭Learning:‬ ‭Introduction,‬ ‭Types:‬ ‭Partitioning,‬ ‭Density‬ ‭Based,‬ ‭DBSCAN,‬
‭Distribution‬ ‭Model-Based,‬ ‭Hierarchical,‬ ‭Agglomerative‬ ‭and‬ ‭Divisive,‬ ‭Common‬ ‭Distance‬ ‭Measures,‬
‭K-Means Clustering Algorithms, Case Study on Clustering for solving real world problems.‬

‭Unit V‬
‭Deep‬‭Learning‬‭Architectures:‬‭Machine‬‭Learning‬‭and‬‭Deep‬‭Learning,‬‭Representation‬‭Learning,‬‭Width‬
‭and‬‭Depth‬‭of‬‭Neural‬‭Networks,‬‭Activation‬‭Functions:‬‭RELU,‬‭LRELU,‬‭ERELU,‬‭Unsupervised‬‭Training‬
‭of‬ ‭Neural‬ ‭Networks,‬ ‭Restricted‬ ‭Boltzmann‬ ‭Machines,‬ ‭Convolutional‬ ‭Neural‬ ‭Networks:‬ ‭Architectural‬
‭Overview,‬ ‭Motivation,‬ ‭Layers,‬ ‭Filters,‬ ‭Parameter‬ ‭sharing,‬ ‭Regularization,‬ ‭Popular‬‭CNN‬‭Architectures,‬
‭Deep Learning Applications.‬
‭Centre for Artificial Intelligence‬
‭RECOMMENDED BOOKS:‬
‭1.‬ ‭Artificial Intelligence: A Modern Approach by Stuart J. Russell and Peter Norvig, Prentice Hall.‬
‭2.‬ ‭Artificial Intelligence: Elaine Rich, Kevin Knight, Mc-Graw Hill.‬
‭3.‬ ‭Introduction to AI & Expert System: Dan W. Patterson, PHI.‬
‭4.‬ ‭Pattern Recognition and Machine Learning, Christopher M. Bishop‬
‭5.‬ ‭Introduction to Machine Learning using Python: Sarah Guido‬
‭6.‬ ‭Machine Learning in Action: Peter Harrington‬

‭COURSE OUTCOMES‬
‭After completing the course, the student will be able to:‬
‭CO1. describe the fundamental concepts of Artificial Intelligence and Machine Learning.‬
‭CO2: design heuristics driven search solutions for real-world problems.‬
‭CO3. identify machine learning based real world problem.‬
‭CO4. design Artificial Intelligence enabled intelligent systems for solving real world problems.‬
‭CO5. analyze Artificial Intelligence and machine learning algorithms.‬
‭CO6. evaluate the performance of Artificial Intelligence and machine learning techniques.‬

‭CO-PO Mapping Matrix‬


‭PO1‬ ‭PO2‬ ‭PO3‬ ‭PO4‬ ‭PO5‬ ‭PO6‬ ‭PO7‬ ‭PO8‬ ‭PO9‬ ‭PO10‬ ‭PO11‬ ‭PO12‬ ‭PSO1‬ ‭PSO2‬
‭CO1‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭3‬ ‭2‬
‭CO2‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬ ‭2‬ ‭3‬ ‭3‬
‭CO3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭3‬ ‭3‬ ‭2‬
‭CO4‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭2‬ ‭3‬ ‭2‬ ‭3‬ ‭3‬
‭CO5‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭3‬ ‭2‬
‭CO6‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬ ‭3‬ ‭2‬
‭Centre for Artificial Intelligence‬
‭NATURAL LANGUAGE PROCESSING‬
‭(2270621/2280621)‬

‭COURSE OBJECTIVES‬
‭●‬ ‭To illustrate the concepts, techniques and application of natural language processing (NLP).‬
‭●‬ ‭To understand linguistic phenomena, grammar and their hierarchy.‬
‭●‬ ‭To introduce real world problems and solutions of NLP and their relation to linguistics and statistics.‬
‭Unit I‬
I‭ ntroduction:‬ ‭Brief‬‭History,‬‭steps,‬‭stages‬‭and‬‭application‬‭involved‬‭in‬‭natural‬‭language‬‭processing,‬‭goals‬
‭of‬ ‭NLP,‬ ‭issues‬ ‭and‬ ‭challenges‬ ‭in‬ ‭NLP,‬ ‭basic‬ ‭concepts‬ ‭of‬ ‭phases‬ ‭of‬ ‭natural‬ ‭language‬ ‭processing‬
‭morphological‬ ‭analysis,‬ ‭syntactic‬ ‭analysis,‬ ‭semantic‬ ‭analysis,‬ ‭pragmatic‬ ‭analysis,‬ ‭tools‬‭and‬‭techniques‬
‭used‬ ‭for‬ ‭performing‬ ‭this‬ ‭analysis,‬ ‭ambiguities,‬ ‭Homonymy,‬ ‭Hyponymy,‬ ‭Hypernymy,‬ ‭Meronymy,‬
‭Synonymy, Antonymy, Polysemy ambiguity in nlp.‬
‭ nit II‬
U
‭ tructure‬ ‭of‬ ‭Words:‬ ‭Words‬ ‭and‬ ‭Their‬ ‭Components,‬ ‭Issues‬ ‭and‬ ‭Challenges,‬ ‭Morphological‬ ‭parsing,‬
S
‭Morphological‬ ‭analysis,‬ ‭Inflectional‬ ‭and‬ ‭derivational‬ ‭morphology,‬ ‭Combining‬ ‭FST‬ ‭Lexicon‬‭and‬‭rules,‬
‭Regular Expressions and finite Automata.‬
‭ nit III‬
U
‭ yntax‬ ‭Analysis:‬ ‭Rule‬ ‭based‬ ‭,‬ ‭stochastic‬ ‭based‬ ‭part‬ ‭of‬ ‭speech‬ ‭tagging,‬ ‭Transformation‬ ‭based‬‭tagging.‬
S
‭Treebanks:‬ ‭A‬ ‭Data-Driven‬ ‭Approach‬ ‭to‬ ‭Syntax,‬ ‭Parsing‬ ‭with‬ ‭context‬ ‭free‬ ‭grammars,‬ ‭context‬ ‭free‬
‭grammar,‬ ‭Probabilistic‬ ‭context‬ ‭free‬ ‭grammars,‬ ‭problems‬ ‭with‬ ‭probabilistic‬ ‭context‬ ‭free‬ ‭grammars‬ ‭,‬
‭multiple‬ ‭tags‬ ‭and‬ ‭words,‬ ‭unknown‬ ‭words,‬ ‭Representation‬ ‭of‬ ‭Syntactic‬ ‭Structure,‬ ‭Parsing‬ ‭Algorithms,‬
‭Models for Ambiguity Resolution in Parsing, top up and bottom up parsing, Multilingual Issues.‬
‭ nit IV‬
U
‭ emantic‬ ‭Analysis‬ ‭and‬ ‭Language‬ ‭Modelling:‬ ‭Semantic‬ ‭Analysis‬ ‭,‬ ‭Relation‬ ‭among‬ ‭lexemes‬ ‭and‬ ‭their‬
S
‭senses,‬ ‭Internal‬ ‭Structure‬ ‭of‬ ‭words,‬ ‭Language‬ ‭model‬ ‭Introduction‬ ‭Hidden‬ ‭Markov‬ ‭Models,‬ ‭and‬ ‭the‬
‭Viterbi‬ ‭Algorithm,‬ ‭N-Gram‬ ‭Models,‬ ‭Language‬ ‭Model‬ ‭Evaluation,‬ ‭Parameter‬ ‭Estimation,‬ ‭Language‬
‭Model‬‭Adaptation,‬‭Types‬‭of‬‭Language‬‭Models,‬‭Language-Specific‬‭Modeling‬‭Problems,‬‭Multilingual‬‭and‬
‭Cross Lingual Language Modeling.‬
‭ nit V‬
U
‭ pplication:‬ ‭Word‬ ‭net,‬ ‭fastext,‬ ‭CBOW‬ ‭,‬ ‭Skip‬ ‭gram,‬ ‭word‬ ‭sense‬ ‭disambiguation,‬ ‭information‬‭retrieval‬
A
‭system,‬‭machine‬‭translation,‬‭question‬‭answer‬‭system,‬‭text‬‭categorization‬‭system,‬‭sentiment‬‭analysis‬‭,‬‭text‬
‭summarization system.‬
‭Centre for Artificial Intelligence‬
‭RECOMMENDED BOOKS‬
‭1.‬ ‭Language processing An introduction to Natural Language Processing, Computational Linguistics and‬
‭speech Recognition by Daniel Jurafsky and James H. Martin‬
‭2.‬ ‭Natural Language Processing with Python by Steven Bird, Ewan Klein, Edward Lopper Multilingual‬
‭3.‬ ‭Natural Language Processing Applications: From Theory to Practice – Daniel M. Bikel and Imed‬
‭Zitouni, Pearson Publication‬
‭4.‬ ‭Natural Language Processing and Information Retrieval: Tanvier Siddiqui, U.S. Tiwary.‬
‭REFERENCE BOOK‬
‭1.‬ ‭Handbook of Natural Language Processing, Second Edition—NitinIndurkhya, Fred J. Damerau, Fred‬
‭J. Damera.‬
‭COURSE OUTCOMES‬
‭After completion of the course students will be able to:‬
‭CO1 : explain the fundamentals of natural language processing‬
‭CO2: analyse the structure of word in NLP‬
‭CO3: differentiate between different types of ambiguities in NLP.‬
‭CO4: evaluate the role of syntactic and semantic of sentences in nlp‬
‭CO5: design different language modelling Techniques‬
‭CO6: create NLP based solutions to real world problems.‬

‭CO-PO Mapping Matrix‬


‭PO1‬ ‭PO2‬ ‭PO3‬ ‭PO4‬ ‭PO5‬ ‭PO6‬ ‭PO7‬ ‭PO8‬ ‭PO9‬ ‭PO10‬ ‭PO11‬ ‭PO12‬ ‭PSO1‬ ‭PSO2‬
‭CO1‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬ ‭1‬ ‭2‬ ‭1‬
‭CO2‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬
‭CO3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭2‬ ‭2‬ ‭1‬ ‭2‬ ‭1‬ ‭1‬ ‭2‬ ‭1‬
‭CO4‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭1‬ ‭3‬ ‭2‬ ‭2‬
‭CO5‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭2‬ ‭3‬ ‭2‬ ‭1‬
‭CO6‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬
‭Centre for Artificial Intelligence‬
‭ EEP LEARNING‬
D
‭(2270623/ 2280623)‬

‭COURSE OBJECTIVES‬
‭●‬ ‭To understand the theoretical foundations, algorithms and methodologies of neural networks‬
‭●‬ ‭To design and develop an application using specific deep learning models‬
‭●‬ ‭To provide practical knowledge in handling and analyzing real world applications.‬

‭Unit I‬
‭ undamentals‬ ‭about‬ ‭Deep‬ ‭Learning.‬ ‭Perception‬ ‭Learning‬ ‭Algorithms.‬ ‭Early‬ ‭Neural‬ ‭Networks.‬ ‭How‬
F
‭Deep‬ ‭Learning‬ ‭is‬ ‭different‬ ‭from‬ ‭Machine‬ ‭Learning.‬ ‭Building‬ ‭Blocks‬ ‭of‬ ‭Neural‬ ‭Network.‬ ‭Optimizers.‬
‭Activation‬ ‭Functions.‬ ‭Loss‬ ‭Functions.‬ ‭Data‬ ‭Pre-processing‬ ‭for‬ ‭neural‬ ‭networks,‬ ‭Feature‬ ‭Engineering.‬
‭Overfitting and Underfitting. Hyperparameters.‬
‭ nit II‬
U
‭Deep‬ ‭Learning‬ ‭Architectures:‬ ‭Machine‬ ‭Learning‬ ‭and‬ ‭Deep‬ ‭Learning,‬ ‭Representation‬ ‭Learning,‬ ‭Width‬
‭and‬‭Depth‬‭of‬‭Neural‬‭Networks,‬‭Activation‬‭Functions:‬‭RELU,‬‭LRELU,‬‭ERELU,‬‭Unsupervised‬‭Training‬
‭of Neural Networks, Restricted Boltzmann Machines, Auto Encoders, Deep Learning Applications‬
‭Unit III‬
‭Convolutional‬‭Neural‬‭Networks:‬‭Architectural‬‭Overview,‬‭Motivation,‬‭Layers,‬‭Filters,‬‭Parameter‬‭sharing,‬
‭Regularization,‬ ‭Popular‬ ‭CNN‬ ‭Architectures:‬ ‭ResNet,‬ ‭AlexNet‬ ‭–‬ ‭Applications;‬ ‭Transfer‬ ‭learning‬
‭Techniques, Variants of CNN: DenseNet, PixelNet.‬
‭Unit IV‬
‭Sequence‬‭Modeling‬‭–‬‭Recurrent‬‭and‬‭Recursive‬‭NETS:‬‭Recurrent‬‭Neural‬‭Networks,‬‭Bidirectional‬‭RNNs,‬
‭Encoder-decoder‬ ‭sequence‬ ‭to‬ ‭sequence‬ ‭architectures‬ ‭-‬ ‭BPTT‬ ‭for‬ ‭training‬ ‭RNN,‬ ‭Long‬ ‭Short‬ ‭Term‬
‭Memory Networks.‬
‭Unit V‬
‭Auto‬ ‭Encoders:‬ ‭Under‬ ‭complete‬ ‭Auto‬ ‭encoder,‬ ‭Regularized‬ ‭Autoencoder,‬ ‭stochastic‬ ‭Encoders‬ ‭and‬
‭Decoders,‬ ‭Contractive‬ ‭Encoders;‬ ‭DEEP‬ ‭GENERATIVE‬ ‭MODELS:‬ ‭Deep‬ ‭Belief‬ ‭networks,‬ ‭Boltzmann‬
‭Machines, Deep Boltzmann Machine, Generative Adversarial Networks.‬
‭Centre for Artificial Intelligence‬
‭RECOMMENDED BOOKS‬
‭1.‬ ‭Ian Goodfellow, YoshuaBengio and Aaron Courville, “ Deep Learning”, MIT Press, 2017‬
‭2.‬ ‭Josh Patterson, Adam Gibson, Deep Learning: A Practitioner’s Approach, O’Reilly Media, 2017‬
‭3.‬ ‭Umberto Michelucci “Applied Deep Learning. A Case-based Approach to Understanding Deep‬
‭4.‬ ‭Neural Networks” A press, 2018.‬
‭5.‬ ‭Giancarlo Zaccone, Md. Rezaul Karim, Ahmed Menshawy, Deep Learning with TensorFlow:‬
‭6.‬ ‭Explore neural networks with Python, Packt Publisher, 2017‬
‭7.‬ ‭Antonio Gulli, Sujit Pal Deep Learning with Keras Packt Publishers, 2017.‬
‭8.‬ ‭Francois Chollet, Deep Learning with Python, Manning Publications, 2017.‬

‭COURSE OUTCOMES‬
‭After completion of the course students will be able to:‬
‭CO1: illustrate the concepts of neural networks, activation functions and optimization algorithms.‬
‭CO2: explain the principles of backpropagation and gradient descent.‬
‭CO3: select an appropriate deep learning model for problem solving.‬
‭CO4: evaluate the performance of deep learning models.‬
‭CO5: compare the applicability of deep learning architectures across the problem domain.‬
‭CO6: develop novel deep learning architectures for specific applications.‬
‭CO-PO Mapping Matrix‬
‭PO1‬ ‭PO2‬ ‭PO3‬ ‭PO4‬ ‭PO5‬ ‭PO6‬ ‭PO7‬ ‭PO8‬ ‭PO9‬ ‭PO10‬ ‭PO11‬ ‭PO12‬ ‭PSO1‬ ‭PSO2‬
‭CO1‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭3‬ ‭3‬ ‭3‬
‭CO2‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭3‬ ‭3‬ ‭3‬
‭CO3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬
‭CO4‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭2‬ ‭3‬ ‭3‬ ‭3‬
‭CO5‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭3‬ ‭3‬ ‭1‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬
‭CO6‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬
‭Centre for Artificial Intelligence‬

‭Syllabi‬
‭of‬
‭Open Category Courses (OC)‬
‭B. Tech VI Semester‬
‭[for the students of other department]‬
‭for batch admitted in 2022-23‬
‭(under the flexible curriculum)‬
‭Centre for Artificial Intelligence‬
‭INFORMATION SECURITY (OC-1)‬

‭COURSE OBJECTIVES‬
‭●‬ ‭To provide conceptual understanding of information security principles, issues, challenges and‬
‭mechanisms.‬
‭●‬ ‭To understand encryption techniques for securing data in transit across data networks.‬

‭Unit-I‬
‭Security:‬ ‭Principles‬‭and‬‭Attacks,‬‭Basic‬‭Number‬‭Theory,‬‭Fundamentals‬‭of‬‭Cryptography,‬‭Steganography,‬
‭Cryptanalysis,‬ ‭Code‬ ‭Breaking,‬ ‭Block‬ ‭Ciphers‬ ‭and‬ ‭Steam‬ ‭Ciphers,‬ ‭Substitution‬ ‭Ciphers,‬ ‭Transposition‬
‭Ciphers, Caesar Cipher, Play-Fair Cipher, Hill Cipher‬
‭Unit-II‬
‭Cryptography:‬ ‭Symmetric‬ ‭Key‬ ‭Cryptography,‬ ‭Public‬ ‭Key‬ ‭Cryptography,‬ ‭Principles‬ ‭of‬ ‭Public‬ ‭Key‬
‭Cryptosystem,‬ ‭Classical‬ ‭Cryptographic‬ ‭Algorithms:‬ ‭RC4,‬ ‭RSA,‬ ‭Distribution‬ ‭of‬ ‭Public‬ ‭Keys‬ ‭and‬ ‭Key‬
‭Management, Diffie-Hellman Key Exchange.‬
‭Unit-III‬
‭Hash‬ ‭Functions:‬ ‭Hash‬ ‭Functions,‬ ‭One‬ ‭Way‬ ‭Hash‬ ‭Function,‬ ‭SHA‬ ‭(Secure‬ ‭Hash‬ ‭Algorithm).‬
‭Authentication:‬ ‭Requirements,‬ ‭Functions,‬ ‭Kerberos,‬ ‭Message‬ ‭Authentication‬ ‭Codes,‬ ‭Digital‬ ‭Signatures,‬
‭Digital Certificates.‬
‭Unit -IV‬
‭IP‬ ‭Web‬ ‭Security‬ ‭Overview:‬ ‭SSL‬‭(Secure‬‭Socket‬‭Layer),‬‭TLS‬‭(Transport‬‭Layer‬‭Security),‬‭SET‬‭(Secure‬
‭Electronic Transaction). IDS (Intrusion detection system), Firewalls: Types, Functionality and Polices.‬
‭Unit -V‬
‭Phishing:‬‭Attacks‬‭and‬‭its‬‭Types,‬‭Buffer‬‭Overflow‬‭Attack,‬‭Session‬‭Hijacking,‬‭Hacker:‬‭Hacking‬‭and‬‭Types‬
‭of‬‭Hackers,‬‭FootPrinting,‬‭Scanning:‬‭Types:‬‭Port,‬‭Network,‬‭Vulnerability),‬‭Sniffing‬‭in‬‭Shared‬‭and‬‭Switched‬
‭Networks, Sniffing Detection Prevention, Spoofing.‬
‭Centre for Artificial Intelligence‬
‭RECOMMENDED BOOKS‬

‭1.‬ ‭Cryptography and Network Security, William Stallings, Pearson Education.‬


‭2.‬ ‭Cryptography and Network Security, Atul Kahate, McGraw Hill Education.‬
‭3.‬ ‭Incident Response and Computer Forensics, Kevin Mandia, Chris Prosise, Tata McGraw Hill.‬

‭COURSE OUTCOMES‬
‭After completion of the course students would be able to:‬
‭CO1: determine symmetric and public key cryptography, classical algorithms, and basic number theory.‬
‭CO2: explain the working of various cryptographic algorithms.‬
‭CO3. apply firewall, IDS, and security protocols like SSL, TLS, and SET.‬
‭CO4: build secure systems using digital signatures, message authentication, and certificates.‬
‭CO5: examine the strengths and weaknesses of IP and web security.‬
‭CO6: select strategies for detecting and preventing attacks like sniffing, spoofing, and hacking.‬

‭CO-PO Mapping Matrix‬


‭PO1‬ ‭PO2‬ ‭PO3‬ ‭PO4‬ ‭PO5‬ ‭PO6‬ ‭PO7‬ ‭PO8‬ ‭PO9‬ ‭PO10‬ ‭PO11‬ ‭PO12‬
‭CO1‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭3‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬
‭CO2‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭3‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬
‭CO3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭3‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬ ‭2‬ ‭3‬
‭CO4‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬ ‭3‬
‭CO5‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭2‬ ‭2‬ ‭3‬
‭CO6‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭1‬ ‭1‬ ‭1‬ ‭2‬ ‭3‬ ‭3‬
‭Centre for Artificial Intelligence‬
‭DATA MINING & WAREHOUSING (OC-1)‬

‭COURSE OBJECTIVES‬
‭●‬ ‭To understand the significance of data mining in a real-world perspective. and gain the understanding‬
‭of data mining techniques, algorithms and commonly used tools.‬
‭●‬ ‭To develop the ability for applying data mining techniques and tools for solving real-world problems.‬

‭Unit I‬
‭Introduction:‬ ‭Motivation,‬ ‭importance,‬ ‭Data‬ ‭types‬ ‭for‬ ‭Data‬ ‭Mining:‬ ‭Relational‬ ‭Databases,‬ ‭Data‬
‭Ware-Houses.‬ ‭Transactional‬ ‭Databases,‬ ‭Advanced‬ ‭Database‬ ‭System‬ ‭and‬‭Its‬‭Applications,‬‭Data‬‭Mining‬
‭Functionalities,‬ ‭Concept/Class‬ ‭Description,‬ ‭Association‬ ‭Analysis‬ ‭Classification‬ ‭&‬ ‭Prediction,‬ ‭Cluster‬
‭Analysis, Outliner Analysis, Classification of Data Mining Systems, Major Issues in Data Mining.‬
‭Unit II‬
‭Data‬ ‭Pre-processing:‬ ‭Data‬ ‭Cleaning,‬ ‭Data‬ ‭Integration‬ ‭and‬ ‭Transformation‬ ‭and‬ ‭Data‬ ‭Reduction.‬
‭Discretization‬ ‭and‬ ‭Concept‬ ‭Hierarchy‬ ‭Generation.‬ ‭Data‬ ‭Mining‬ ‭Primitives‬ ‭Languages‬ ‭and‬ ‭System‬
‭Architectures,‬‭Concept‬‭Description,‬‭Characterization‬‭and‬‭Comparison‬‭Analytical,‬‭Characterization.‬‭Data‬
‭Warehouse‬‭and‬‭OLTP‬‭Technology‬‭for‬‭Data‬‭Mining:‬‭Differences‬‭between‬‭Operational‬‭Database‬‭Systems‬
‭&‬ ‭Data‬ ‭Warehouse,‬ ‭Multidimensional‬ ‭Data‬ ‭Model,‬ ‭Data‬ ‭Warehouse‬ ‭Architecture,‬ ‭Data‬ ‭Warehouse‬
‭Implementation, Data Cube Technology‬
‭Unit III‬
‭Mining‬ ‭Association‬ ‭Rules‬ ‭in‬ ‭Large‬ ‭Databases:‬ ‭Association‬ ‭Rule‬ ‭Mining:‬ ‭Market‬ ‭Basket‬ ‭Analysis,‬
‭Basic‬ ‭Concepts,‬ ‭Mining‬ ‭Single‬‭Dimensional‬‭Boolean‬‭Association‬‭Rules‬‭from‬‭Transactional‬‭Databases:‬
‭The‬‭Apriori‬‭Algorithm,‬‭Generating‬‭Association‬‭Rules‬‭from‬‭Frequent‬‭Items,‬‭Improving‬‭the‬‭Efficiency‬‭of‬
‭Apriori,‬‭other‬‭Algorithms‬‭&‬‭their‬‭Comparison,‬‭Mining‬‭Multilevel‬‭Association‬‭Rules,‬‭Multidimensional‬
‭Association Rules, Constraint Based Association Rule Mining.‬
‭Unit IV‬
‭Classification‬ ‭&‬ ‭Prediction‬ ‭and‬ ‭Cluster‬ ‭Analysis:‬ ‭Issues‬ ‭Regarding‬ ‭Classification‬ ‭&‬ ‭Prediction,‬
‭Different‬ ‭Classification‬ ‭Methods,‬ ‭Prediction,‬ ‭Cluster‬ ‭Analysis,‬ ‭Major‬ ‭Clustering‬ ‭Methods,‬ ‭Currently‬
‭Available Tools.‬
‭Unit V‬
‭Introduction‬‭to‬‭data‬‭warehousing,‬‭need‬‭and‬‭significance,‬‭challenges‬‭&‬‭issues‬‭in‬‭warehousing,‬‭difference‬
‭between‬ ‭data‬ ‭mining‬‭&‬‭warehousing,‬‭case‬‭studies-‬‭stock‬‭market,‬‭super‬‭market‬‭etc.‬‭,‬‭implementation‬‭of‬
‭current applications involving data mining.‬
‭Centre for Artificial Intelligence‬
‭RECOMMENDED BOOKS‬
‭1.‬ ‭Data Mining: Concepts and Techniques, Han and Kamber, Morgan Kaufmann Publications.‬
‭2.‬ ‭Data Mining Techniques, A. K. Pujari, Universities Press Pvt. Ltd.‬
‭3.‬ ‭Data Warehousing in the Real World, Sam Anahory, Pearson Publication.‬

‭COURSE OUTCOMES‬
‭After completion of the course students will be able to:‬
‭CO1: explain fundamental concepts of data mining and data warehousing.‬
‭CO2: classify database systems and data models of data warehouses.‬
‭CO3: compare methods for storing & retrieving data from different data sources.‬
‭CO4: apply data mining techniques for knowledge extraction from large amounts of data.‬
‭CO5: predict trends to make informed decisions.‬
‭CO6: develop real world applications using data mining techniques.‬

‭CO-PO Mapping Matrix‬


‭PO1‬ ‭PO2‬ ‭PO3‬ ‭PO4‬ ‭PO5‬ ‭PO6‬ ‭PO7‬ ‭PO8‬ ‭PO9‬ ‭PO10‬ ‭PO11‬ ‭PO12‬
‭CO1‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭2‬ ‭1‬ ‭1‬ ‭1‬ ‭1‬ ‭3‬
‭CO2‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭1‬ ‭1‬ ‭2‬ ‭1‬ ‭3‬
‭CO3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭2‬ ‭1‬ ‭2‬ ‭3‬
‭CO4‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭3‬ ‭3‬
‭CO5‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭2‬ ‭2‬ ‭2‬ ‭3‬
‭CO6‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭3‬ ‭2‬ ‭3‬ ‭3‬
‭Centre for Artificial Intelligence‬

‭Experiment list/ Lab manual/ Skill Based Mini-Project List‬


‭of‬
‭Laboratory Courses offered‬
‭for‬
‭B. Tech VI Semester‬
‭[Information Technology (Artificial Intelligence and‬
‭Robotics)/ Artificial Intelligence (AI) and Data Science/‬
‭Artificial Intelligence (AI) and Machine Learning]‬
‭for batch admitted in 2022-23‬
‭(under the flexible curriculum)‬
‭Centre for Artificial Intelligence‬
‭IMAGE PROCESSING (2240622/2270622/2280622)‬

‭LIST OF PROGRAMS‬

‭1.‬ ‭Study of Image Processing:‬


‭a.‬ ‭Image Acquisition‬
‭b.‬ ‭Image Enhancement‬
‭c.‬ ‭Color image Processing‬
‭d.‬ ‭Image resizing‬
‭2.‬ ‭Write a program for Image resampling.‬
‭3.‬ ‭Write a program for color detection.‬
‭4.‬ ‭Write a program for image Segmentation.‬
‭5.‬ ‭Write a program for object Detection.‬
‭6.‬ ‭Write a program for hand Gesture Recognition.‬
‭7.‬ ‭Write a program for object Tracking.‬
‭8.‬ ‭Image enhancement and spatial operation- Convolution, correlation, linear filtering,edge detection.‬
‭9.‬ ‭Implement i) Edge Detection, ii) Line Detection.‬
‭10.‬ ‭Implement Smoothing and Sharpening of an eight bit color image.‬

‭COURSE OUTCOMES‬
‭After completing the course, the student will be able to:‬
‭CO1: develop the ability to write programs for color detection.‬
‭CO2: analyze color information in digital images.‬
‭CO3: apply image segmentation techniques to partition images into meaningful regions.‬
‭CO4: demonstrate competence in writing a program for object detection.‬
‭CO5: integrate image processing techniques to interpret and respond to hand gestures.‬
‭CO6: track movement of objects in a sequence of images.‬
‭Centre for Artificial Intelligence‬
‭IMAGE PROCESSING (2240622/2270622/2280622)‬

‭SKILL BASED MICRO PROJECTS‬


‭1.‬ ‭Write a program to implement linear point operation and clipping,‬
‭2.‬ ‭Write a program to implement thresholding and negation‬
‭3.‬ ‭Write a program to implement non-linear mapping and intensity slicing,‬
‭4.‬ ‭Write a program to implement image histogram and histogram equalization‬
‭5.‬ ‭Write a program to implement data compression‬

‭SKILL BASED MACRO PROJECTS‬

‭ .‬
1 ‭ rite a program to Implement Smoothing and Sharpening of an eight bit color image‬
W
‭2.‬ ‭Write a program to Implement Low Pass Filter‬
‭3.‬ ‭Write a program to Implement High Pass Filter‬
‭4.‬ ‭Write a program to Implement Arithmetic Mean Filter‬
‭5.‬ ‭Write a program to Implement Geometric Mean Filter‬

‭SKILL BASED MINI PROJECTS‬

‭ .‬
1 ‭ olor image processing - color models, color enhancement, color thresholding.‬
C
‭2.‬ ‭Frequency domain operations- fourier transform, freq domain filtering‬
‭3.‬ ‭Implement the spatial image enhancement functions on a bitmap image –Mirrorin (Inversion)‬
‭4.‬ ‭Implement the spatial image enhancement functions on a bitmap image –Rotation (Clockwise)‬
‭5.‬ ‭Implement the spatial image enhancement functions on a bitmap image –Enlargement (Double Size)‬
‭Centre for Artificial Intelligence‬

‭ARTIFICIAL INTELLIGENCE & MACHINE LEARNING (2240623)‬

‭LIST OF PROGRAMS‬
‭1.‬ ‭Introduction to python programming, its advantages/disadvantages and Libraries.‬
‭2.‬ ‭Implement classification problem using ANN.‬
‭3.‬ ‭Write a python program to perform BFS.‬
‭4.‬ ‭Write a python program to perform DFS.‬
‭5.‬ ‭Study and implement various Dimensionality reduction, Feature selection and Normalization‬
‭techniques in Python‬
‭6.‬ ‭Implement Linear Regression model in Python‬
‭7.‬ ‭With the help of Support vector machine algorithm classify any suitable dataset‬
‭8.‬ ‭available over the trusted repository.‬
‭9.‬ ‭Implement the Decision tree Algorithm for a given dataset.‬
‭10.‬ ‭Implement the Random Forest Algorithm for a given dataset.‬
‭11.‬ ‭Implement the k-means clustering Algorithm for a given dataset.‬
‭12.‬ ‭Implement the DBSCAN Algorithm for a given dataset.‬
‭13.‬ ‭Design and implementation of Classification using CNN with the help of available libraries in python.‬

‭COURSE OUTCOMES‬
‭After completing the course, the student will be able to:‬
‭CO1: apply concepts of python programming to implement artificial intelligence based algorithms.‬
‭CO2: implement ML models in Python using machine learning libraries such as Scikit-Learn.‬
‭CO3: build k-means and hierarchical clustering model.‬
‭CO4: use the functions of NLTK and spaCy Python libraries for text classification and sentiment analysis.‬
‭CO5: perform feature engineering and optimize machine learning models.‬
‭CO6: apply AI and ML techniques to solve real world problems.‬
‭Centre for Artificial Intelligence‬
‭ARTIFICIAL INTELLIGENCE & MACHINE LEARNING (2240623)‬

‭SKILL BASED MINI PROJECTS‬

‭ .‬
1 ‭ esign and implement Handwritten Digits Recognition system.‬
D
‭2.‬ ‭Design and implement a Spam classification system using Machine Learning algorithm.‬
‭3.‬ ‭Design and implement a Music Recommendation App.‬
‭4.‬ ‭Design and implement heart disease prediction using different classification algorithms and analyze the‬
‭best over the dataset.‬
‭5.‬ ‭Design and implementation of Animal Kingdom Classification using CNN with the help of available‬
‭libraries in python.‬
‭6.‬ ‭Apply the classification algorithms over the time series dataset by transforming the dataset into static‬
‭values.‬
‭7.‬ ‭With the help of random forest classifier, classify any suitable dataset available over the trusted‬
‭repository.‬
‭8.‬ ‭Design a program for Number Guessing using a random number generator library. Make a play game‬
‭with the defined library.‬
‭9.‬ ‭Implement a movie recommendation system using any algorithm over the dataset from‬
‭10.‬ ‭trusted repository.‬
‭11.‬ ‭Optimize the performance of your classification algorithm using the applicable optimization algorithm‬
‭like swarm based, genetic algorithm.‬

‭SKILL BASED MACRO PROJECTS‬

‭ .‬ ‭Apply PCA for dimensionality reduction in a given dataset.‬


1
‭2.‬ ‭Apply LDA for dimensionality reduction in a given dataset.‬
‭3.‬ ‭Implement Filter method for feature selection‬
‭4.‬ ‭Implement Wrapper method for feature selection‬
‭5.‬ ‭Plot correlation matrix using MATPLOTLIB‬
‭6.‬ ‭Identify the missing value in a given dataset and replace it with mean value‬
‭7.‬ ‭Identify the missing value in a given dataset and replace it with median value‬
‭8.‬ ‭Identify the distribution properties (skewness, standard deviation etc.) in a given dataset.‬
‭9.‬ ‭Write a program to identify the outliers in a given dataset.‬
‭10.‬ ‭Write a program to plot the confusion matrix of a classifier.‬

‭SKILL BASED MICRO PROJECTS‬


‭1.‬ ‭Apply MAX-MIN normalization in a given dataset‬
‭2.‬ ‭Apply standardization in a given dataset‬
‭3.‬ ‭Apply binary hot encoding in a given dataset‬
‭4.‬ ‭Apply multiclass encoding in a given dataset‬
‭5.‬ ‭Plot a histogram plot of a given dataset‬
‭6.‬ ‭Plot a bar, box and scatter plot and heat map of a given dataset‬
‭7.‬ ‭Provide statistical description (mean, median, mode etc.) of a given datasets‬
‭Centre for Artificial Intelligence‬
‭DEEP LEARNING (2270623/ 2280623)‬
‭List of Programs‬
‭1.‬ ‭Train a Deep learning model to classify a given image using pre trained model‬
‭2.‬ ‭Object detection using Convolution Neural Network‬
‭3.‬ ‭Recommendation system from sales data using Deep Learning‬
‭4.‬ ‭Improve the Deep learning model by tuning hyper parameters‬
‭5.‬ ‭Perform Sentiment Analysis in network graph using RNN‬
‭6.‬ ‭Image generation using GAN‬
‭7.‬ ‭Develop a model by using AUTO ENCODERS.‬
‭8.‬ ‭Implement an LSTM based Autoencoder in TensorFlow/Keras.‬
‭9.‬ ‭Perform Sentiment Analysis using RNN‬
‭10.‬ ‭Using a pre-trained model on Keras for Transfer Learning.‬
‭11.‬ ‭Getting started with the python 3.x and installing libraries of Tensorflow, Keras, Pytorch.‬
‭12.‬ ‭Write a python program to perform tokenization by word and sentence using nltk‬
‭13.‬ ‭Create a python based application to eliminate stopwords using nltk.‬
‭14.‬ ‭Perform stemming using nltk in python.‬
‭15.‬ ‭Write a python program to perform lemmatization using nltk.‬
‭16.‬ ‭Perform Parts of Speech tagging using Hidden Markov Model‬
‭17.‬ ‭Perform Parts of Speech tagging using Viterbi Decoding‬
‭18.‬ ‭Implement chunking using nltk in python.‬
‭19.‬ ‭Implement Named Entity Recognition using nltk‬
‭20.‬ ‭Create an application which finds all unigrams, bigrams and trigrams present in the given corpus.‬

‭Course Outcomes of Lab:‬


‭After completion of the course students will be able to:‬
‭CO1: recognize the characteristics of deep learning models that are useful to solve real-world problems‬
‭CO2: design Convolution Neural Network for solving various problems pertaining to image processing.‬
‭CO3: apply deep learning model variants for implementing NLP based applications‬
‭CO4: examine the working mechanism of different deep learning algorithms.‬
‭CO5: solve real world problems using NLP techniques‬
‭CO6: develop autoencoders and generative models for suitable applications.‬
‭Centre for Artificial Intelligence‬

‭DEEP LEARNING (270603/ 280603)‬

‭List of Skill based Mini Projects‬


‭List of Micro Projects:‬
‭1.‬ ‭Implement a regression model in Keras.‬
‭2.‬ ‭Explain existing and emerging deep learning architectures for text and speech processing.‬
‭3.‬ ‭Hyper-Parameter Tuning in Multilayer Perceptron‬
‭4.‬ ‭Deep learning Packages Basics: Tensorflow, Keras, Theano and PyTorch‬
‭5.‬ ‭Classification of MNIST Dataset using CNN‬
‭6.‬ ‭Parameter Tuning in CNN‬
‭7.‬ ‭Implement a perceptron in TensorFlow/Keras Environment.‬

‭List of Macro Projects:‬


‭1.‬ ‭Implement simple vector addition in TensorFlow.‬
‭2.‬ ‭Implement an Image Classifier using CNN in TensorFlow/Keras.‬
‭3.‬ ‭Face recognition using CNN‬
‭4.‬ ‭Object detection using Transfer Learning of CNN architectures‬
‭5.‬ ‭Recommendation system using Deep Learning‬
‭6.‬ ‭Dimensionality Reduction using Deep learning‬
‭7.‬ ‭Language Modeling using RNN‬

‭List of Mini Projects:‬


‭1.‬ ‭Classification with Multilayer Perceptron using Scikit-learn (MNIST Dataset)‬
‭2.‬ ‭Time Series Prediction using RNN‬
‭3.‬ ‭Sentiment Analysis using LSTM‬
‭4.‬ ‭Image generation using GAN‬
‭5.‬ ‭Deep Learning using H2O‬
‭6.‬ ‭Deep Learning using DL4J‬
‭7.‬ ‭Use deep learning to solve real-life problem‬
‭8.‬ ‭Predictive analysis using H2O tool‬
‭9.‬ ‭Using a pre trained model on Keras for Transfer Learning‬
‭10.‬ ‭Recommendation system from sales data using Deep Learning.‬
‭Centre for Artificial Intelligence‬
‭11.‬ ‭Build a Python-based summarization tool to condense lengthy documents while retaining key‬
‭information.‬
‭12.‬ ‭Develop a model using TensorFlow to classify news articles as reliable or fake.‬
‭13.‬ ‭Create a spam filter that classifies SMS messages as spam or legitimate using Python.‬
‭14.‬ ‭Design a system to identify abusive language or hate speech in online comments.‬
‭15.‬ ‭Implement a Python-based NER system to identify and categorize entities like names, dates, and‬
‭locations.‬
‭16.‬ ‭Build a tool that generates effective and unique research paper titles using NLP techniques.‬
‭17.‬ ‭Develop a Python program to identify and correct spelling and grammatical errors in text.‬
‭18.‬ ‭Create a predictive text tool to suggest the next word or phrase in a sentence using context.‬
‭19.‬ ‭Implement a chatbot capable of engaging in natural, human-like conversations using NLP models.‬
‭20.‬ ‭Develop a Python-based sentiment analysis to classify text as positive, negative, or neutral.‬

You might also like