Final Syllabus Updated - MS in Artificial Intelligence PDF

Annexure-III M.S. in Artificial Intelligence Jointly by Deen Dayal Upadhyaya Gorakhpur University, Gorakhpur...

Annexure-III M.S. in Artificial Intelligence Jointly by Deen Dayal Upadhyaya Gorakhpur University, Gorakhpur & National Institute of Electronics and Information Technology, Gorakhpur (An Autonomous Scientific Society of Ministry of Electronics and Information Technology, Government of India)  M. S. – ARTIFICIAL INTELLIGENCE The horizon trembles with the dawn of a new era, an era where silicon hums with sentience and steel muscles with purpose – the era of Artificial Intelligence. From robotic surgeons wielding scalpels with a surgeon's precision to intelligent assistants anticipating your every need before you even whisper them, AI is no longer a futuristic fantasy, but an intricate thread woven into the fabric of our lives. It has transformed industries, redefined human-machine interaction, and stands poised to revolutionize the very way we experience the world. This is the threshold you stand upon, poised to step into the vanguard of this transformative surge. The M.S. in Artificial Intelligence program jointly run by Deen Dayal Upadhyaya Gorakhpur University and NIELIT Gorakhpur is your gateway to becoming a leader in this electrifying field. Meticulously crafted by industry titans and academic visionaries, this curriculum transcends mere learning to ignite a deep understanding of AI's core principles. It equips you not just with the tools, but with the power to unlock its boundless potential. You will delve into the mathematical bedrock of machine learning, where equations become more than symbols, but pathways to understanding how intelligent systems learn and evolve from data. You will master the art of supervised learning, wielding regression and classification algorithms as if a sculptor shapes clay, unlocking the power to predict and automate. Unsupervised learning will become your microscope, revealing hidden patterns and insights within sprawling datasets, like detective unearthing secrets in a tangled web of clues. This journey extends beyond algorithms and equations, delving into the ethical compass of AI development. You will learn to navigate the intricate landscape of research methodology and intellectual property rights, ensuring your contributions to this powerful technology are responsible and impactful. Program Education Objectives (PEO) PEO1: To equip students with a comprehensive understanding of mathematical foundations, machine learning techniques, and optimization strategies, enabling them to apply this knowledge effectively in solving complex real-world problems. PEO2: To foster a research-oriented mindset and encourage innovation in the field of machine learning. Graduates should be capable of conducting independent research, contributing to advancements in machine learning techniques, and developing novel solutions to emerging challenges. PEO3: To promote ethical practices, intellectual property rights awareness, and holistic development. Graduates should possess strong communication skills, an understanding of societal implications, and a commitment to values such as sustainability, social responsibility, and continuous learning. Program Outcomes (PO) PO1: Graduates independently solve complex challenges in ML, showcasing research skills and proposing effective solutions. PO2: Graduates exhibit proficient oral and written skills, empowering them to articulate technical concepts and collaborate effectively within interdisciplinary teams. PO3: Graduates embrace lifelong learning, adapting to evolving ML trends, technologies, and methodologies for sustained professional development. PO4: Graduates contribute innovatively to ML, applying advanced algorithms and AI, demonstrating research competence, and fostering technological advancements. PO5: Graduates uphold ethical standards, respecting intellectual property, considering societal impacts, and responsibly contributing to social, environmental, and ethical considerations. DDUGU-NIELIT: M.S. in Artificial Intelligence 1  Course Category Wise Credit Distribution Category Credits Program Core 39 Core Labs 8 Electives 9 Open Electives 6 Project / Dissertation 23 Total 85 Course Structure Semester - I S. No. Course Code Course Name L P C Program Core - I 1. AIL101 Mathematical Foundations for Machine 3 0 3 Learning Program Core - II 2. AIL102 3 0 3 Data Structure using Python Program Core - III 3. AIL103 3 0 3 Data Mining & Warehousing Program Core - IV 4. AIL104 3 0 3 Soft Computing Program Core - V 5. AIL105 3 0 3 Introduction to Artificial Intelligence Program Core - VI 6. AIL106 3 0 3 Research Methodology and IPR Laboratory - I 7. AIP101 Python Programming & Data Structure 0 4 2 using Python Laboratory - II 8. AIP102 0 4 2 Data Mining & Soft Computing DDUGU-NIELIT: M.S. in Artificial Intelligence 2  Semester - II S. No. Course Code Course Name L P C Program Core - VII 1. AIL201 3 0 3 Machine Learning Techniques Program Core - VIII 2. AIL202 3 0 3 Deep Learning Techniques Program Core - IX 3. AIL203 3 0 3 Optimization Techniques Program Core - X 4. AIL204 3 0 3 Natural Language Computing Program Core - XI 5. AIL205 Problem Solving Methods in Artificial 3 0 3 Intelligence No 6. ACL*** Audit Course 2 0 Credits Laboratory - III 7. AIP206 Machine Learning & Deep Learning 0 4 2 Lab Laboratory - IV 8. AIP207 Natural Language Computing & AI 0 4 2 Lab 9. AID208 Mini project with Seminar 0 4 2 Semester - III S. No. Course Code Course Name L P C Program Core - XII 1. AIL301 Artificial Intelligence and Knowledge 3 0 3 Representation 2. AEL*** Program Elective - III 3 0 3 3. AEL*** Program Elective - IV 3 0 3 4. AEL*** Program Elective - V 3 0 3 5. OEL*** Open Elective - I 3 0 3 6. AID302 Dissertation - I 0 12 6 DDUGU-NIELIT: M.S. in Artificial Intelligence 3  Semester - IV S. No. Course Code Course Name L P C Program Core - XIII 1. AIL401 3 0 3 Video Analytics using AI 2. OEL*** Open Elective - II 3 0 3 3. AID402 Dissertation - II 0 30 15 Elective Courses S. No. Course Code Course Name L P C 1. AEL201 Design Thinking 3 0 3 2. AEL202 Advanced Algorithms and Analysis 3 0 3 3. AEL203 Data Warehousing and Pattern Mining 3 0 3 4. AEL204 Big Data Analytics 3 0 3 5. AEL205 Information Retrieval 3 0 3 6. AEL206 Pattern Recognition 3 0 3 Introduction to High Performance 7. AEL207 3 0 3 Computing 8. AEL208 Computer Vision 3 0 3 9. AEL209 Social Media Analytics 3 0 3 10. AEL210 Blockchain 3 0 3 11. AEL211 Healthcare Data Analytics 3 0 3 12. AEL212 Cognitive Systems 3 0 3 DDUGU-NIELIT: M.S. in Artificial Intelligence 4  Audit Courses S. No. Course Code Course Name L P C 1. ACL201 English for Research Paper Writing 2 0 2. ACL202 Disaster Management 2 0 3. ACL203 Sanskrit for Technical Knowledge 2 0 4. ACL204 Value Education 2 0 No 5. ACL205 Constitution of India Credits 2 0 6. ACL206 Pedagogy Studies 2 0 7. ACL207 Stress Management by Yoga 2 0 Personality Development through Life 8. ACL208 2 0 Enlightenment Skills Open Electives S. No. Course Code Course Name L P C 1. OEL201 Business Analytics 3 0 3 2. OEL202 Industrial Safety 3 0 3 3. OEL203 Operations Research 3 0 3 4. OEL204 Cost Management of Engineering Projects 3 0 3 5. OEL205 Composite Materials 3 0 3 6. OEL206 Waste to Energy 3 0 3 DDUGU-NIELIT: M.S. in Artificial Intelligence 5  Core Subjects Program Core - I Subject Code AIL101 Course Name Mathematical Foundations for Machine Learning Credits 3 COURSE OBJECTIVE After completion of this course, students should be able to: 1. Understand the fundamental mathematical principles and theories relevant to machine learning. 2. Apply mathematical concepts to analyze and interpret machine learning algorithms and models. 3. Develop a proficiency in using mathematical tools and techniques to design, implement, and optimize machine learning algorithms. Total Number of Lectures: 48 NO. OF LECTURE WITH BREAKUP LECTURES Unit 1: Set Theory, Relations and Functions, Combinatorics, Graph Theory, Propositional Logic, Predicate Logic, Mathematical Induction, Recurrence Relations, 8 Discrete Probability, Number Theory, Permutations and Combinations, Discrete Structures, Lattices, Boolean Algebra, Algorithms and Complexity Theory. Unit 2: Algebraic Structures, Groups, Rings, Fields, Partial Orders, Posets, Homomorphisms, Isomorphisms, Substructures, Quotient Structures, Fundamental Theorem of Homomorphisms, Fundamental Theorem of Isomorphisms, Direct 10 Products, Cosets and Lagrange's Theorem, Normal Subgroups, Factor Groups, Field Extensions, Algebraic Closure, Galois Theory. Unit 3: Introduction to Automata Theory, Finite Automata, Deterministic Finite Automata (DFA), Non-deterministic Finite Automata (NFA), Regular Languages, Regular Expressions, Context-Free Languages, Context-Free Grammars, Pushdown 10 Automata (PDA), Turing Machines, Chomsky Hierarchy, Pumping Lemma, Myhill- Nerode Theorem, Closure Properties of Regular and Context-Free Languages. Unit 4: Decidability and Undecidability, Church-Turing Thesis, Recursively Enumerable Languages, Halting Problem, Reducibility, Post Correspondence Problem, Computability Theory, Universal Turing Machine, Rice's Theorem, Formal 10 Languages and Their Applications, Lexical Analysis, Syntax Analysis, Parsing Techniques, Compiler Design. Unit 5: Propositional Calculus, First-order Logic, Predicate Calculus, Inference Rules, Resolution, Semantic Tableaux, Logical Equivalence, Normal Forms, 10 Quantifiers, Model Theory, Soundness and Completeness, Automated Reasoning, Knowledge Representation, Ontologies, Expert Systems, Logical Agents. COURSE OUTCOME 1. Proficiency in fundamental mathematical concepts. 2. Gain insight into advanced mathematical topics relevant to machine learning. 3. Enhancement of their critical thinking skills and develop the ability to approach machine DDUGU-NIELIT: M.S. in Artificial Intelligence 6  learning problems. DDUGU-NIELIT: M.S. in Artificial Intelligence 7 Recommended Readings 1. "Mathematics for Machine Learning" by Marc Peter Deisenroth, A Aldo Faisal, and Cheng Soon Ong 2. "Pattern Recognition and Machine Learning" by Christopher M. Bishop 3. "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville 4. "Introduction to Probability" by Joseph K. Blitzstein and Jessica Hwang DDUGU-NIELIT: M.S. in Artificial Intelligence 8  Program Core - II Subject Code AIL102 Course Name Data Structure using Python Credits 3 COURSE OBJECTIVE After completion of this course, students should be able to: 1. Develop students' programming skills in Python. 2. Enhance students' problem-solving abilities through hands-on exercises and projects. 3. Provide students with opportunities to apply data structures and algorithms to practical programming tasks. Total Number of Lectures: 48 NO. OF LECTURE WITH BREAKUP LECTURES Unit 1: Introduction to Python Programming: Python Basics, Data Types & Variables, Control Flow (if-else, loops), Functions, Modules and Packages, File Handling, Exception Handling, Object-Oriented Programming in Python, 8 Inheritance, Polymorphism, Encapsulation, Abstraction, Python Libraries and Frameworks. Unit 2: Data Structures in Python: Lists, Tuples, Sets, Dictionaries, Stacks, Queues, Linked Lists, Trees, Binary Search Trees (BST), Graphs, Heaps, Hash 10 Tables, Arrays, Time and Space Complexity Analysis, Circular Buffers, Deques. Unit 3: Advanced Data Structures: Balanced Trees (AVL Trees, Red-Black Trees), Priority Queues, Disjoint Sets, Trie, Segment Trees, Fenwick Trees (Binary 10 Indexed Trees), Bloom Filters, Skip Lists, Suffix Trees, B-trees, B+ Trees, Radix Trees, K-d Trees, Patricia Tries, Rope Data Structures. Unit 4: Algorithmic Techniques in Python: Sorting Algorithms (Bubble Sort, Selection Sort, Insertion Sort, Merge Sort, Quick Sort), Searching Algorithms 10 (Linear Search, Binary Search), Recursion, Dynamic Programming, Greedy Algorithms, Divide and Conquer, Backtracking. Unit 5: Python Libraries: Algorithms NumPy, pandas, matplotlib, scikit-learn, TensorFlow, PyTorch, NetworkX, SciPy, BeautifulSoup, NLTK, Django, Flask, 10 SQLAlchemy, pytest, OpenCV, Plotly, Seaborn, NLTK, Statsmodels. COURSE OUTCOME 1. Understanding Python Programming languages. 2. Demonstration of a thorough understanding of various data structures. 3. Enhancement of their problem-solving abilities through hands-on exercises and projects. 4. Ability to analyze the time and space complexity of algorithms and data structures. Recommended Readings 1. "Problem Solving with Algorithms and Data Structures using Python" by Bradley N. Miller and David L. Ranum 2. "Python Data Structures and Algorithms" by Benjamin Baka 3. "Data Structures and Algorithms in Python" by Michael T. Goodrich, Roberto Tamassia, and Michael H. Goldwasser DDUGU-NIELIT: M.S. in Artificial Intelligence 9  4. "Data Structures and Algorithms Using Python" by Rance D. Necaise DDUGU-NIELIT: M.S. in Artificial Intelligence 10  Program Core - III Subject Code AIL103 Course Name Data Mining & Warehousing Credits 3 COURSE OBJECTIVE After completion of this course, students should be able to: 1. Introduce students to the fundamental concepts, processes, and methodologies of data mining. 2. Familiarize students with the concepts and architecture of data warehouses, data marts, and online analytical processing (OLAP) systems. 3. Provide students with practical experience in designing and implementing pattern mining. Total Number of Lectures: 48 NO. OF LECTURE WITH BREAKUP LECTURES Unit 1: Introduction to Data Mining and Warehousing Overview of data mining and warehousing, Historical development, Importance in decision-making, Basic 7 concepts in data mining, Data preprocessing techniques, Data warehouse architecture, OLAP (Online Analytical Processing) fundamentals. Unit 2: Data Preprocessing and Cleaning Data cleaning techniques, Data integration and transformation, Handling missing and noisy data, Dimensionality reduction 7 methods, Feature selection and extraction, Data discretization techniques. Unit 3: Data Mining Techniques Classification and prediction techniques, Association rule mining, Clustering algorithms, Sequential pattern mining, Text 8 mining methods, Web mining techniques, Social media analytics. Unit 4: Advanced Topics in Data Mining Ensemble methods, Deep learning for data mining, Stream mining, Big data analytics, Spatial data mining, Temporal data 12 mining, Imbalanced data analysis, Ethical considerations in data mining. Unit 5: Data Warehousing and Business Intelligence Data warehouse design and implementation, ETL (Extract, Transform, Load) process, Multidimensional 14 modeling, Data mart design, Reporting and visualization tools, Business intelligence applications, Data mining in business decision-making. COURSE OUTCOME 1. Demonstrate proficiency in data warehousing concepts. 2. Apply various data mining techniques and algorithms to extract actionable insights from large datasets. 3. Gain practical experience in designing, implementing, and managing data warehouses. Recommended Readings 1. "Data Warehousing Fundamentals" by Paulraj Ponniah 2. "Introduction to Data Mining" by Pang-Ning Tan, Michael Steinbach, and Vipin Kumar 3. "The Data Warehouse Toolkit: The Definitive Guide to Dimensional Modeling" by Ralph Kimball and Margy Ross 4. "Principles of Data Mining" by David J. Hand, Heikki Mannila, and Padhraic Smyth DDUGU-NIELIT: M.S. in Artificial Intelligence 11  5. "Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management" by Gordon Program Core - IV Course Code AIL104 Course Name Soft Computing Credits 3 COURSE OBJECTIVE 1. To introduce the concepts and techniques of building blocks of Artificial Intelligence and Soft Computing techniques and their difference from conventional techniques. 2. To generate an ability to design, analyze and perform experiments on real life problems using various Neural Network algorithms. 3. To conceptualize Fuzzy Logic and its implementation for various real-world applications. 4. To provide the understanding of Genetic Algorithms and its applications in developing solutions to real-world problems. Total Number of Lectures: 48 NO. OF LECTURE WITH BREAKUP LECTURES Unit 1: Introduction: What is computational intelligence?- Biological basis for neural networks- Biological versus Artificial neural networks- Biological basis for evolutionary computation- Behavioral motivations for fuzzy logic, Myths about computational intelligence- Computational intelligence application areas, 10 Evolutionary computation, computational intelligence-Adoption, Types, self- organization and evolution, Historical views of computational intelligence, Computational intelligence and Soft computing versus Artificial intelligence and Hard computing. Unit 2: Evolutionary Computation Concepts and Paradigms- History of evolutionary computation & overview, Genetic algorithms, Evolutionary programming &strategies, Genetic programming, Particle swarm optimization, 10 Evolutionary computation implementations-Implementation issues, Genetic algorithm implementation, Particle swarm optimization implementation. Unit 3: Neural Network Concepts and Paradigms- What Neural Networks are? Why they are useful, Neural network components and terminology- Topologies - Adaptation, Comparing neural networks and other information Processing 10 methods- Stochastic- Kalman filters - Linear and Nonlinear regression - Correlation - Bayes classification -Vector quantization -Radial basis functions - Preprocessing - Post processing. Unit 4: Fuzzy Systems Concepts and Paradigms - Fuzzy sets and Fuzzy logic - Approximate reasoning, Developing a fuzzy controller - Fuzzy rule system 5 implementation. Unit 5: Performance Metrics- General issues- Partitioning the patterns for training, testing, and Validation-Cross validation - Fitness and fitness functions - Parametric and nonparametric statistics, Evolutionary algorithm effectiveness 13 metrics, Receiver operating characteristic curves, Computational intelligence tools for explanation facilities, Case Studies for implementation of practical applications in computational intelligence. Recent Trends in deep learning, DDUGU-NIELIT: M.S. in Artificial Intelligence 12 various classifiers, neural networks and genetic algorithm, Implementation of recently proposed soft computing techniques. COURSE OUTCOME After completion of course, students would be able to: 1. Identify and describe soft computing techniques and their roles in building intelligent machines 2. Apply fuzzy logic and reasoning to handle uncertainty and solve various engineering problems. 3. Apply genetic algorithms to combinatorial optimization problems. 4. Evaluate and compare solutions by various soft computing approaches for a given problem. Recommended Readings 1. "Soft Computing: Techniques and its Applications in Electrical Engineering" by M. N. Ahmadi. 2. "Introduction to Soft Computing: Neuro-Fuzzy and Genetic Algorithms" by Sivanandam, S. N., & Deepa, S. N. 3. "Soft Computing: Fundamentals and Applications" by Ajith Abraham. 4. "Soft Computing: A Fusion of Foundations, Methodologies and Applications" edited by Lotfi A. Zadeh, Janusz Kacprzyk, and Ronald R. Yager. 5. "Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence" by Jang, J. S. R., Sun, C. T., & Mizutani, E. DDUGU-NIELIT: M.S. in Artificial Intelligence 13 Program Core - V Course Code AIL105 Course Name Introduction to Artificial Intelligence Credits 3 COURSE OBJECTIVE 1. To familiarize students with the fundamental concepts, theories, and applications of artificial intelligence. 2. To gain insight into the various subfields of AI, such as machine learning, natural language processing, computer vision, and robotics. Total Number of Lectures: 48 NO. OF LECTURE WITH BREAKUP LECTURES Unit 1: Introduction of AI, Definition of AI, birth of AI, brief history of AI, Future of Artificial Intelligence, Turing test, Types of environment, Types of agents, Characteristics of Intelligent Agents, typical Intelligent Agents, PEAS 10 (Performance measure, Environment, Actuators, Sensors). Applications of Artificial Intelligence in real word. Unit 2: Problem Solving Approach to Typical AI problems, Problem solving Methods. Introduction to searching & Search Strategies, Uninformed, Informed, Heuristics, Hill climbing, A*, AO* Algorithms, Local Search Algorithms and Optimization Problems. Searching with Partial Observations, Constraint 10 Satisfaction Problems, Constraint Propagation, Backtracking Search, Game Playing, mini-max algorithm, optimal decisions in multiplayer games, Problem in Game playing, Alpha, Beta Pruning, Stochastic Games, Evaluation functions. Unit 3: Knowledge representation issues, predicate logic- logic programming, semantic nets- frames and inheritance, constraint propagation, representing knowledge using rules, rules based deduction systems. Reasoning under 10 uncertainty, review of probability, Baye’s probabilistic interferences and dempstershafer theory. Unit 4: First order logic. Inference in first order logic, propositional vs. first order inference, unification & lifts forward chaining, Backward chaining, Resolution, 8 Learning from observation Inductive learning, Decision trees, Explanation based learning, Statistical Learning methods, Reinforcement Learning. Unit 5: Expert systems:- Introduction, basic concepts, structure of expert systems, the human element in expert systems how expert systems works, problem areas addressed by expert systems, expert systems success factors, types of expert systems, expert systems and the internet interacts web, knowledge engineering, scope of knowledge, difficulties, in knowledge 10 acquisition methods of knowledge acquisition, machine learning, intelligent agents, selecting an appropriate knowledge acquisition method, societal impacts reasoning in artificial intelligence, inference with rules, with frames: model based reasoning, case based reasoning, explanation & meta knowledge inference with uncertainty representing uncertainty. COURSE OUTCOME 1. Understand concepts of Artificial Intelligence and different types of intelligent agents and their architecture. DDUGU-NIELIT: M.S. in Artificial Intelligence 14  2. Formulate problems as state space search problem & efficiently solve them. 3. Understand the working of various informed and uninformed searching algorithms and different heuristics 4. Understand concept of knowledge representation i.e. propositional logic, first order logic. Recommended Readings 1. "Artificial Intelligence: A Modern Approach" by Stuart Russell and Peter Norvig. 2. "Artificial Intelligence: Foundations of Computational Agents" by David L. Poole and Alan K. Mackworth. 3. "Pattern Recognition and Machine Learning" by Christopher M. Bishop. 4. "Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 5. "Artificial Intelligence: Structures and Strategies for Complex Problem Solving" by George F. Luger and William A. Stubblefield. References 1. Patrick Henry Winston, Artificial Intelligence, Third Edition, Addison-Wesley Publishing Company. 2. Nils J. Nilsson, Principles of Artificial Intelligence, Illustrated Reprint Edition, Springer Heidelberg. 3. Stuart Russell and Peter Norvig. Artificial Intelligence: A Modern Approach, PHI. 4. Nils J. Nilsson, Quest for Artificial Intelligence, First Edition, Cambridge University Press. 5. N. P. Padhy – Artificial Intelligence and Intelligence Systems, OXFORD publication. 6. B. Yagna Narayana - Artificial Neural Networks, PHI DDUGU-NIELIT: M.S. in Artificial Intelligence 15 Program Core - VI Course Code AIL106 Course Name Research Methodology and IPR