Skip to content
CampusPrep

RGPV B.Tech · 3rd Year

AIML 6th Semester Syllabus

Artificial Intelligence & Machine Learning (AIML): the official syllabus of all 8 6th sem subjects, unit by unit, with previous year papers, notes and important questions. Free to read.

Subjects

AIML 6th semester syllabus, unit by unit

Every subject of RGPV Artificial Intelligence & Machine Learning 6th semester (3rd year), as the official syllabus lists it.

Theory of Computation (TOC)

AL-601

  1. Unit 1Introduction to Automata Theory

    Examples of automata machines · Finite Automata as language acceptor and translator · Moore machines · Mealy machines · Composite machine · Conversion from Mealy to Moore and vice versa

  2. Unit 2Types of Finite Automata

    Non‑deterministic Finite Automata (NFA) · Deterministic Finite Automata (DFA) · Conversion of NFA to DFA · Minimization of automata · Regular expressions · Arden’s theorem · Language operations: union, intersection, concatenation, closure · Two‑way DFA

  3. Unit 3Grammars

    Types of grammar · Context‑sensitive grammar · Context‑free grammar (CFG) · Regular grammar · Derivation trees · Ambiguity in grammar · Simplification of CFG · Conversion of grammar to automata and vice versa · Chomsky hierarchy of grammars · Elimination of null and unit productions · Chomsky Normal Form (CNF) · Greibach Normal Form (GNF)

  4. Unit 4Pushdown Automata

    Examples of Pushdown Automata (PDA) · Deterministic PDA · Non‑deterministic PDA · Conversion of PDA to CFG and vice versa · CFG equivalent to PDA · Petri‑net model for PDA

  5. Unit 5Turing Machines and Decidability

    Construction techniques for Turing machines · Universal Turing machine · Multi‑tape, multi‑head and multidimensional Turing machines · NP‑complete problems · Decidable and recursively enumerable languages · Decidability · Undecidable languages · Halting problem · Post correspondence problem

Computer Networks (CN)

AL-602

  1. Unit 1Computer Network: Definitions, goals, components, Architecture, Classifications & Types; Layered Architecture; ISO/OSI Reference Model; Physical Layer Principles

    Definitions, goals, components, architecture, classifications and types of computer networks. · Protocol hierarchy and layered architecture, including design issues, interfaces and services. · Connection‑oriented and connectionless services and associated service primitives. · ISO/OSI reference model and its comparison with the TCP/IP model. · Physical layer principles: transmission media, bandwidth, data rate and modulation schemes.

  2. Unit 2Data Link Layer

    Data link layer functions: services, framing, flow control and error control. · Elementary and sliding‑window protocols (1‑bit, Go‑Back‑N, Selective‑Repeat, Hybrid ARQ). · Protocol verification using finite‑state‑machine and Petri‑net models. · ARP, RARP and GARP protocols.

  3. Unit 3MAC Sub‑layer

    MAC sub‑layer addressing and the Binary Exponential Back‑off (BEB) algorithm. · Random access and contention schemes (ALOHA, Slotted ALOHA, CSMA, CSMA/CD, CSMA/CA). · Collision‑free protocols (Basic Bit Map, BRAP, Binary Count Down, MLMA, Adaptive Tree Walk). · Performance‑measuring metrics for MAC protocols. · IEEE 802 series standards and their variants.

  4. Unit 4Network Layer

    Network layer services, design issues and routing algorithms (Least‑Cost, Dijkstra, Bellman‑Ford, hierarchical, broadcast, multicast). · IP addressing, header format, packet forwarding, fragmentation and reassembly. · ICMP functionality. · Comparative study of IPv4 and IPv6.

  5. Unit 5Transport and Application Layers

    Transport layer design issues, UDP header format, checksum and support for unicast/multicast real‑time traffic. · TCP connection management, reliability mechanisms, flow control, congestion control, header format and timer management. · Application layer protocols: HTTP/WWW, FTP, SSH, SMTP/MIME/IMAP, DNS, and network management (SNMP).

Image and Video Processing (IVP)

AL-603 (A)

  1. Unit 1Module 1

    Image representation and analysis · Introduction to computer vision · Numerical representation of images · Image augmentation · Image enhancement · Image processing · Color transforms · Geometric transforms · Feature recognition and extraction

  2. Unit 2Module 2

    Image segmentation · Object detection · Breaking image into parts · Finding contours and edges of objects · Background subtraction for video

  3. Unit 3Module 3

    Object motion and tracking · Tracking a single point over time · Motion models for object movement · Analyzing videos as sequences of frames · Tracking a set of features over time · Matching features between frames · Tracking a moving car using optical flow

  4. Unit 4Module 4

    Robotic localization · Bayesian statistics for robot positioning · Sensor measurements for navigation · Gaussian uncertainty · Histogram filter for robot localization in Python

  5. Unit 5Module 5

    Image restoration · Degradation model · Noise models · Estimation of degradation function · Restoration using Wiener filters · Restoration using inverse filters

Data and Visual Analytics (DVA)

AL-603 (B)

  1. Unit 1Data Definitions and Analysis Techniques

    Elements · Variables · Data categorization · Levels of measurement · Data management and indexing · Introduction to statistical concepts · Sampling distributions · Resampling · Statistical inference · Descriptive statistics · Measures of central tendency · Measures of location of dispersions

  2. Unit 2Advanced Data Analysis Techniques

    Statistical hypothesis generation and testing · Chi‑Square test · t‑Test · Analysis of variance (ANOVA) · Correlation analysis · Maximum likelihood test · Regression modelling · Multivariate analysis · Bayesian modelling · Inference and Bayesian network · Regression analysis

  3. Unit 3Data Wrangling

    Introduction to data wrangling · Gathering data · Assessing data · Cleaning data · Design of visualizations · Univariate exploration of data · Bivariate exploration of data · Multivariate exploration of data · Explanatory visualizations

  4. Unit 4Data Ecosystem

    Overview of the data analyst ecosystem · Types of data · Understanding different file formats · Sources of data · Overview of data repositories · NoSQL databases · Data marts · Data lakes · ETL processes and data pipelines · Foundations of big data · Big data processing tools (Hadoop, HDFS, Hive, Spark)

  5. Unit 5Data Visualization Tools

    Python visualization libraries (matplotlib, pandas, seaborn, ggplot, plotly) · Introduction to PowerBI tools · Industry project examples – creating visualizations of complex datasets

Pattern Recognition (PR)

AL-603 (C)

  1. Unit 1Introduction and Mathematical Preliminaries

    Principles of pattern recognition · Uses of pattern recognition · Mathematics for pattern recognition · Classification and Bayesian rules · Clustering vs classification · Basics of linear algebra and vector spaces · Eigenvalues and eigenvectors · Rank of matrix · Singular Value Decomposition (SVD)

  2. Unit 2Pattern Recognition Basics

    Bayesian decision theory · Classifiers · Discriminant functions · Decision surfaces · Parameter estimation methods · Hidden Markov models · Dimension reduction methods · Fisher discriminant analysis · Principal component analysis (PCA) · Non‑parametric techniques for density estimation · Non‑metric methods for pattern classification · Unsupervised learning · Clustering algorithms: K‑means · Clustering algorithms: Hierarchical clustering · Other clustering methods

  3. Unit 3Feature Selection and Extraction

    Problem statement and uses of feature selection · Branch‑and‑bound algorithm for feature selection · Sequential forward selection · Sequential backward selection · Cauchy‑Schwarz inequality in feature selection · Probabilistic separability based feature selection criteria · Inter‑class distance based feature selection criteria · Principles of feature extraction

  4. Unit 4Visual Recognition

    Human visual recognition system · Low‑level modelling (e.g., feature extraction) · Mid‑level abstraction (e.g., segmentation) · High‑level reasoning (e.g., scene understanding) · Detection and segmentation methods · Context and scene analysis · Importance and saliency detection · Large‑scale search and recognition · Egocentric vision systems · Human‑in‑the‑loop interactive systems · 3‑D scene understanding

  5. Unit 5Recent Advancements in Pattern Recognition

    Comparison of classifier performance · Basics of statistics for pattern recognition · Covariance and its properties · Data condensation techniques · Feature clustering · Data visualization · Probability density estimation · Visualization and aggregation methods · Fuzzy C‑Means (FCM) and soft‑computing techniques · Examples of real‑life datasets

Cloud Computing (CC)

AL-604 (A)

  1. Unit 1Introduction of Grid and Cloud Computing

    Introduction of Grid and Cloud computing · Characteristics · Components · Business and IT perspective · Cloud services requirements · Cloud models · Security in public model · Public versus private clouds · Cloud computing platforms: Amazon EC2 · Platform as Service: Google App Engine · Microsoft Azure · Utility Computing · Elastic Computing

  2. Unit 2Cloud Services

    SAAS · PAAS · IAAS · Cloud design and implementation using SOA · Conceptual cloud model · Cloud stack · Computing on demand · Information life cycle management · Cloud analytics · Information security · Virtual desktop infrastructure · Storage cloud

  3. Unit 3Virtualization Technology

    Definition · Benefits · Sensor virtualization · HVM · Study of hypervisor · Logical partitioning (LPAR) · Storage virtualization · SAN · NAS · Cloud server virtualization · Virtualized data center

  4. Unit 4Cloud Security Fundamentals

    Cloud security fundamentals · Vulnerability assessment tool for cloud · Privacy and security in cloud · Cloud computing security architecture: Architectural considerations – general issues · Trusted cloud computing · Secure execution environments and communications · Microarchitectures · Identity management and access control – identity management · Access control · Autonomic security · Cloud computing security challenges – virtualization security management and virtual threats · VM security recommendations · VM-specific security techniques · Secure execution environments and communications in cloud

  5. Unit 5SOA and Cloud

    SOA and cloud · SOA and IAAS · Cloud infrastructure benchmarks · OLAP · Business intelligence · e-Business · ISV · Cloud performance monitoring commands · Issues in cloud computing · QoS issues in cloud · Mobile cloud computing · Inter‑cloud issues · Sky computing · Cloud Computing Platform · Xen Cloud Platform · Eucalyptus · OpenNebula · Nimbus · TPlatform · Apache Virtual Computing Lab (VCL) · Anomaly Elastic Computing Platform

Information Security & Management (ISM)

AL-604 (B)

  1. Unit 1Introduction

    Needs for security · Basic security terminologies (threats, vulnerability, exploit, etc.) · Security principles (Confidentiality, Integrity, Availability) · Authentication · Non‑repudiation · Security attacks and their classifications · Mathematical foundation – prime numbers · Modular arithmetic · Fermat’s and Euler’s theorem · Euclidean algorithm · Chinese Remainder Theorem · Discrete logarithms

  2. Unit 2Symmetric Key Cryptography

    Classical cryptography – substitution and transposition · Cryptanalysis of classical ciphers · Symmetric cryptography algorithms: DES, 3DES, AES · Modes of operation: ECB, CBC, etc. · Linear cryptanalysis · Differential cryptanalysis

  3. Unit 3Asymmetric Key Cryptography

    Key distribution and management · Diffie‑Hellman key exchange algorithm · Asymmetric cryptography algorithms: RSA, ECC · Various attacks on cryptosystems

  4. Unit 4Authentication & Integrity

    Message Authentication Codes (MAC) · Hash functions · SHA, MD5 · HMAC · Digital signatures and authentication protocols · Authorization · Access control mechanisms · X.509 digital certificates

  5. Unit 5E‑mail, IP and Web Security

    E‑mail security: PGP, MIME, S/MIME · IP security protocols · Web security: TLS, SSL · Secure Electronic Transaction (SET) · Firewalls and their types · Introduction to Intrusion Detection and Prevention Systems (IDPS) · Risk management · Security planning

Intelligent Systems for Robotics (ISR)

AL-604 (C)

  1. Unit 1Introduction

    Fundamentals of Robotics · Robot Kinematics – Position Analysis · Dynamic Analysis and Forces · Robot programming languages – three levels of robot programming · Requirements of a robot programming language · Problems peculiar to robot programming languages

  2. Unit 2Need of AI in Robotics

    History and state of the art of AI in robotics · Motivation for AI in robotics · Thinking and acting humanly · Intelligent agents – structure and properties

  3. Unit 3Game Playing

    AI techniques for game playing · Plausible move generator · Static evaluation move generator · Game playing strategies · Problems in game playing

  4. Unit 4Robotics Fundamentals

    Robot classification and specification · Kinematic representations and transformations · Dynamics techniques · Trajectory planning and control

  5. Unit 5Robotics and Its Applications

    DDD concept and intelligent robots · Robot anatomy and definition · Laws of robotics · History and terminology of robotics · Accuracy and repeatability of robots · Specifications, speed, joints and links of robots · Robot classifications and architecture of robotic systems · Robot drive systems – hydraulic, pneumatic and electric