RTU 6th Sem AI & DS Syllabus
Unit-wise

1. Unit 1

   Introduction: Objective, scope and outcome of the course.

   1 hr
2. Unit 2

   Introduction to Image Processing: Digital Image representation, Sampling & Quantization, Steps in image Processing, Image acquisition, color image representation.

   4 hrs
3. Unit 3

   Image Transformation & Filtering: Intensity transform functions, histogram processing, Spatial filtering, Fourier transforms and its properties, frequency domain filters, colour models, Pseudo colouring, colour transforms, Basics of Wavelet Transforms.

   6 hrs
4. Unit 4

   Image Restoration: Image degradation and restoration process, Noise Models, Noise Filters, degradation function, Inverse Filtering, Homomorphism Filtering.

   7 hrs
5. Unit 5

   Image Compression: Coding redundancy, Interpixel redundancy, Psychovisual redundancy, Huffman Coding, Arithmetic coding, Lossy compression techniques, JPEG Compression.

   5 hrs
6. Unit 6

   Image Segmentation & Representation: Point, Line and Edge Detection, Thresholding, Edge and Boundary linking, Hough transforms, Region Based Segmentation, Boundary representation, Boundary Descriptors.

   5 hrs

Total: 28 lecture hours

1. Unit 1

   Introduction: Objective, scope and outcome of the course.

   1 hr
2. Unit 2

   Supervised learning algorithm: Introduction, types of learning, application, Supervised learning: Linear Regression Model, Naive Bayes classifier Decision Tree, K nearest neighbor, Logistic Regression, Support Vector Machine, Random Forest algorithm

   9 hrs
3. Unit 3

   Unsupervised learning algorithm: Grouping unlabelled items using k-means clustering, Hierarchical Clustering, Probabilistic clustering, Association rule mining, Apriori Algorithm, f-p growth algorithm, Gaussian mixture model.

   8 hrs
4. Unit 4

   Introduction to Statistical Learning Theory, Feature extraction - Principal component analysis, Singular value decomposition. Feature selection – feature ranking and subset selection, filter, wrapper and embedded methods, Evaluating Machine Learning algorithms and Model Selection.

   8 hrs
5. Unit 5

   Semi supervised learning, Reinforcement learning: Markov decision process (MDP), Bellman equations, policy evaluation using Monte Carlo, Policy iteration and Value iteration, Q -Learning, State- Action-Reward-State-Action (SARSA), Model -based Reinforcement Learning.

   8 hrs
6. Unit 6

   Recommended system, Collaborative filtering, Content -based filtering Artificial neural network, Perceptron, Multilayer network, Backpropagation, Introduction to Deep learning.

   8 hrs

Total: 42 lecture hours

1. Unit 1

   Introduction: Objective, scope and outcome of the course.

   1 hr
2. Unit 2

   Introduction to security attacks: services and mechanism, classical encryption techniques - substitution ciphers and transposition ciphers, cryptanalysis, stream and block ciphers.

   6 hrs
3. Unit 3

   Modern block ciphers: Block Cipher structure, Data Encryption standard (DES) with example, strength of DES, Design principles of block cipher, AES with structure, its transformation functions, key expansion, example and implementation. Multiple encryption and triple DES, Electronic Code Book, Cipher Block Chaining Mo de, Cipher Feedback mode, Output Feedback mode, Counter mode.

   6 hrs
4. Unit 4

   Public Key Cryptosystems with Applications: Requirements and Cryptanalysis, RSA cryptosystem, Rabin cryptosystem, Elgamal cryptosystem, Elliptic curve cryptosystem.

   6 hrs
5. Unit 5

   Cryptographic Hash Functions, their applications: Simple hash functions, its requirements and security, Hash functions based on Cipher Block Chaining, Secure Hash Algorithm (SHA). Message Authentication Codes, its requirements and security, MACs based on Hash Functions, Macs based on Block Ciphers. Digital Signature, its properties, requirements and security, various digital signature schemes (Elgamal and Schnorr), NIST digital Signature algorithm.

   5 hrs
6. Unit 6

   Key management and distribution: symmetric key distribution using symmetric and asymmetric encryptions, distribution of public keys, X.509 certificates, Public key infrastructure. Remote user authentication with symmetric and asymmetric encryption, Kerberos Web Security threats and approaches, SSL architecture and protocol, Transport layer security, HTTPS and SSH.

   4 hrs

Total: 28 lecture hours

1. Unit 1

   Introduction: Objective, scope and outcome of the course.

   1 hr
2. Unit 2

   Computer Data Representation: Basic computer data types, Complements, Fixed point representation, Register Transfer and Micro-operations: Floating point representation, Register Transfer language, Register Transfer, Bus and Memory Transfers (Tree -State Bus Buffers, Memory Transfer), Arithmetic Micro -Operations, Logic Micro-Operations, Shift Micro -Operations, Arithmetic logical shift unit. Basic Computer Organization and DesignInstruction codes, Computer registers, computer instructions, Timing and Control, Instruction cycle, Memory-Reference Instructions, Input-output and interrupt, Complete computer description, Design of Basic computer, design of Accumulator Unit.

   10 hrs
3. Unit 3

   Programming The Basic Computer: Introduction, Machine Language, Assembly Language, assembler, Program loops, Programming Arithmetic and logic operations, subroutines, I -O Programming. Micro programmed Control: Control Memory, Address sequencing, Micro program Example, design of control Unit

   7 hrs
4. Unit 4

   Central Processing Unit: Introduction, General Register Organization, Stack Organization, Instruction format, Addressing Modes, data transfer and manipulation, Program Control, Reduced Instruction Set Computer (RISC)Pipeline And Vector Processing, Flynn's taxonomy, Parallel Processing, Pipelining, Arithmetic Pipeline, Instruction, Pipeline, RISC Pipeline, Vector Processing, Array Processors

   8 hrs
5. Unit 5

   Computer Arithmetic: Introduction, Addition and subtraction, Multiplication Algorithms (Booth Multiplication Algorithm), Division Algorithms, Floating Point Arithmetic operations, Decimal Arithmetic Unit. Input -Output Organization, Input -Output Interface, Asynchronous Data Transfer, Modes Of Transfer, Priority Interrupt, DMA, Input -Output Processor (IOP), CPUIOP Communication, Serial communication.

   8 hrs
6. Unit 6

   Memory Organization: Memory Hierarchy, Main Memory, Auxiliary Memory, Associative Memory, Cache Memory, Virtual Memory. Multipreocessors: Characteristics of Multiprocessors, Interconnection Structures, Inter -processor Arbitration, Inter - processor Communication and Synchronization, Cache Coherence, Shared Memory Multiprocessors.

   8 hrs

Total: 42 lecture hours

1. Unit 1

   Introduction: Objective, scope and outcome of the course.

   1 hr
2. Unit 2

   Introduction to AI and Intelligent agent: Different Approach of AI, Problem Solving: Solving Problems by Searching, Uninformed search, BFS, DFS, Iterative deepening, Bi directional search, Hill climbing, Informed search techniques: heuristic, Greedy search, A* search, AO* search, constraint satisfaction problems.

   3 hrs
3. Unit 3

   Game Playing: Minimax, alpha-beta pruning, jug problem, chess problem, tiles problem

   6 hrs
4. Unit 4

   Knowledge and Reasoning: Building a Knowledge Base: Propositional logic, first order logic, situation calculus. Theorem Proving in First Order Logic. Planning, partial order planning. Uncertain Knowledge and Reasoning, Probabilities, Bayesian Networks.

   6 hrs
5. Unit 5

   Learning: Overview of different forms of learning, Supervised base learning: Learning Decision Trees, SVM, Unsupervised based learning, Market Basket Analysis, Neural Networks.

   7 hrs
6. Unit 6

   Introduction to Natural Language Processing: Different issue involved in NLP, Expert System, Robotics.

   5 hrs

Total: 28 lecture hours

1. Unit 1

   Introduction: Objective, scope and outcome of the course.

   1 hr
2. Unit 2

   Introduction: Objective, scope and outcome of the course. Introduction Cloud Computing: Nutshell of cloud computing, Enabling Technology, Historical development, Vision, feature Characteristics and components of Cloud Computing. Challenges, Risks and Approaches of Migration into Cloud. Ethical Issue in Cloud Computing, Evaluating the Cloud's Business Impact and economics, Future of the cloud. Networking Support for Cloud Computing. Ubiquitous Cloud and the Internet of Things

   6 hrs
3. Unit 3

   Cloud Computing Architecture: Cloud Reference Model, Layer and Types of Clouds, Services models, Data centre Design and interconnection Network, Architectural design of Compute and Storage Clouds. Cloud Programming and Software: Fractures of cloud programming, Parallel and distributed programming paradigms-Map Reduce, Hadoop, High level Language for Cloud. Programming of Google App engine.

   10 hrs
4. Unit 4

   Virtualization Technology: Definition, Understanding and Benefits of Virtualization. Implementation Level of Virtualization, Virtualization Structure/Tools and Mechanisms, Hypervisor VMware, KVM, Xen. Virtualization: of CPU, Memory, I/O Devices, Virtual Cluster and Resources Management, Virtualization of Server, Desktop, Network, and Virtualization of data-centre.

   10 hrs
5. Unit 5

   Securing the Cloud: Cloud Information security fundamentals, Cloud security services, Design principles, Policy Implementation, Cloud Computing Security Challenges, Cloud Computing Security Architecture. Legal issues in cloud Computing. Data Security in Cloud: Business Continuity and Disaster Recovery, Risk Mitigation, Understanding and Identification of Threats in Cloud, SLA-Service Level Agreements, Trust Management

   8 hrs
6. Unit 6

   Cloud Platforms in Industry: Amazon web services, Google AppEngine, Microsoft Azure Design, Aneka: Cloud Application Platform -Integration of Private and Public Clouds Cloud applications: Protein structure prediction, Data Analysis, Satellite Image Processing, CRM

   7 hrs

Total: 42 lecture hours

Course objectives

1. To understand the biological neural network and to model equivalent neuron models.
2. To understand the architecture, learning algorithm and issues of various feed forward and feedback neural networks.

1. Unit 1

   Introduction: A Neural Network, Human Brain, Models of a Neuron, Neural Networks viewed as Directed Graphs, Network Architectures, Knowledge Representation, Artificial Intelligence and Neural Networks. Learning Process: Error Correction Learning, Memory Based Learning, Hebbian L earning, Competitive, Boltzmann Learning, Credit Assignment Problem, Memory, Adaption, Statistical Nature of the Learning Process.

2. Unit 2

   Single Layer Perceptrons: Adaptive Filtering Problem, Unconstrained Organization Techniques, Linear Least Square Filters, Least Mean Square Algorithm, Learning Curves, Learning Rate Annealing Techniques, Perceptron –Convergence Theorem, Relation Between Perceptron and Bayes Classifier for a Gaussian Environment. Multilayer Perceptron: Back Propagation Algorithm XOR Problem, H euristics, Output Representation and Decision Rule, Computer Experiment, Feature Detection.

3. Unit 3

   Back Propagation: Back Propagation and Differentiation, Hessian Matrix, Generalization, Cross V alidation, Network Pruning Techniques, Virtues and Limitations of Back Propagation Learning, Accelerated Convergence, Supervised Learning.

4. Unit 4

   Self-Organization Maps (SOM): Two Basic Feature Mapping Models, Self -Organization Map, SOM Algorithm, Properties of Feature Map, Computer Simulations, Learning V ector Quantization, Adaptive Patter Classification.

5. Unit 5

   Neuro Dynamics: Dynamical Systems, Stability of Equilibrium States, Attractors, Neuro Dynamical Models, Manipulation of Attractors as a Recurrent Network Paradigm. Hopfield Models – Hopfield Models, Computer Experiment.

Text books

1. Neural Networks a Comprehensive Foundations, Simon Haykin, PHI edition.

Reference books

1. Artificial Neural Networks - B. V egnanarayana Prentice Hall of India P Ltd 2005
2. Neural Networks in Computer Intelligence, Li Min Fu MC GRAW HILL
3. Neural Networks -James A Freeman David M S Kapura Pearson Education 2004.
4. Introduction to Artificial Neural Systems Jacek M. Zurada, JAICO Publishing House Ed. 2006.

Course objectives

1. Understanding biology of Natural Language Processing; Place and Manner of Articulation; Word Boundary Detection; Argmax based computations; Morphology fundamentals; Morphological Diversity of Indian Languages; Morphology Paradigms; Finite State Machine Based Morphology; Automatic Morphology Learning; Shallow Parsing; Named Entities; Maximum Entropy Models; Random Fields.

Course outcomes

1. Learn about major NLP issues and solutions
2. Become agile with NLP programming
3. Be able to asses NLP problems
4. Be able to get the gist of relevant research papers
5. Understand Natural language understanding, processing, generation.

1. Unit 1

   Introduction, Machine Learning and NLP, ArgMax Computation, Syntactic Collocations; More on Term Weighting

2. Unit 2

   Practice with ipython Notebooks, NLTK Text; Adopt a text collection, Tokenize Your Text Collection, Create a First Look at Y our Text Collection, Parts of Speech and Tagging, Part of WSD: WordNet, Wordnet; Application in Query Expansion, Wiktionary; semantic relatedness, Measures of WordNet Similarity, Similarity Measures, Resnick's work on WordNet Similarity.

3. Unit 3

   WordNet Lexical Relations, Work on your Keyphrase assignment, Keyphrase Identification Assignment, Run Keyphrase Extraction on Mystery Text, Names features Parsing Algorithms, Evidence for Deeper Structure; Top Down Parsing Algorithms, Noun Structure; Top Down Parsing Algorithms - contd, Non -noun Structure and Parsing Algorithms

4. Unit 4

   Probabilistic parsing; sequence labeling, PCFG, Probabilistic parsing; PCFG (contd.), Probabilistic parsing: Training issues Pandas Intro and Readings, Read About Syntactic and Semantic Parsing Review, Parsing, and Logic, Kaggle -based Text Classification Assignment

5. Unit 5

   Arguments and Adjuncts, Probabilistic parsing; inside-outside probabilities Text Clustering, Distributional Semantics readings, Clustering and Distributional Semantics Morphology, Graphical Models for Sequence Labelling in NLP, Graphical Models for Sequence Labelling in NLP (contd.)

Text books

1. Natural Language Processing with Python online book: http://www.nltk.org/book/
2. Speech and Language Processing, 2nd Edition 2nd Edition by Daniel Jurafsky, James H. Martin

Reference books

1. Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit 1st Edition by Steven Bird, Ewan Klein, Edward Loper.
2. Applied Text Analysis with Python: Enabling Language-Aware Data Products with Machine Learning 1st Edition by Benjamin Bengfort, Rebecca Bilbro, Tony Ojeda.
3. Natural Language Processing and Computational Linguistics: A practical guide to text analysis with Python, Gensim, spaCy, and Keras Paperback – June 29, 2018 by Bhargav Srivinasa-Desikan.

Course outcomes

1. Understand fundamental concepts of NP-hardness and computational complexity
2. Understand the strengths, weaknesses and appropriateness of nature-inspired algorithms.
3. Apply nature-inspired algorithms to optimization, design and learning problems.
4. Analyse the Behaviour systems of nature inspired algorithm applied in real world problems.
5. Understand the theory behind the design of immune networks and DNA computing and their potential applications.

1. Unit 1

   Evolutionary Systems: Pillars of Evolutionary Theory, The Genotype, Artificial Evolution, Genetic representations, Initial Population, Fitness Functions, Selection and Reproduction, Genetic Operators, Evolutionary Measures, Types of Evolutionary Algorithms

2. Unit 2

   Collective Systems: Particle Swarm Optimization Algorithm, Hybrid PSO algor ithms, Ant Colony Optimization, Artificial Bee Colony, Firefly Algorithm Artificial Neural Networks: History, Mathematical model of neuron, ANN architectures, learning rules Backpropagation network, Backpropagation learning and its applications, V ariants of BPA.

3. Unit 3

   Behaviour in Cognitive Science, Behaviour in Artificial Intelligence, Behaviour -Based Robotics, Biological Inspiration for Robots, Robots as Biological Models, Robot Learning, Evolution of Behavioural Systems Evolution and Learning in Behavioura l Systems, Evolution and Neural Development in Behavioural Systems.

4. Unit 4

   Immuno Computing: Introduction - Immune System, Physiology and main components, Immune Network Theory - Danger Theory, Evaluation Interaction - Immune Algorithms, Bone Marrow Models, Forest's Algorithm, Artificial Immune Networks.

5. Unit 5

   DNA Computing: Motivation, DNA Molecule, Adleman's experiment, Test tube programming language, Universal DNA Computers, PAM Model, Splicing Systems, Lipton's Solution to SA T Problem, Scope of DNA Computing, From Classical to DNA Computing.

Text books

1. Xin-She Yang, “Nature-Inspired Computation and Swarm Intelligence Algorithms, Theory and Applications”, Elsevier, Academic Press, 2020.

Reference books

1. Leandro Nunes de Castro, "Fundamentals of Natural Computing, Basic Concepts, Algorithms and Applications", Chapman & Hall/ CRC, Taylor and Francis Group, 2007.
2. Floreano D. and Mattiussi C., "Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies", MIT Press, Cambridge, MA, 2008.
3. Licheng Jiao, Ronghua Shang, Fang Liu, Weitong Zhang, Brain and Nature-Inspired Learning, Computation and Recognition, Elsevier, 2020.