Syllabus of B. Tech. V Sem AIML (RGPV)

• AL-501 Operating Systems

• AL-502 Database Management Systems

• AL-503 (A) Information Retrieval (Departmental Elective)

• AL-503 (B) Deep Learning (Departmental Elective)

• AL-503(C) Optimization Techniques in Machine Leaning (Departmental Elective)

• AL-504 (A) AI in Health Care (Open Elective)

• AL-504 (B) Natural Language Processing (Open Elective)

• AL-504 (C) Computational Intelligence (Open Elective)

​Syllabus of AL-501 Operating Systems

Source: (rgpv.ac.in)

UNIT-1 : Introduction to Operating Systems

• Function Evolution Different types of Operating Systems

• Desirable Characteristics and features of an O/S.

• Operating Systems Services: Types of Services

• Different ways of providing these Services– Commands System Calls.

• Need of System Calls Low level implementation of System Calls

• Portability issue

• Operating System Structures.

UNIT-2 : File Systems (Secondary Storage Management)

• File Concept User’s and System Programmer’s view of File System

• Hard Disk Organization

• Disk Formatting and File System Creation

• Different Modules of a File System

• Disk Space Allocation Methods – Contiguous Linked Indexed.

• Disk Partitioning and Mounting; Directory Structures File Protection;

• Virtual and Remote File Systems.

• Case Studies of File Systems being used in Unix/Linux & Windows;

• System Calls used in these Operating Systems for file management.

UNIT-3 : Process Management

• Concept of a process Process State Diagram

• Different type of schedulers CPU scheduling algorithms Evaluation of scheduling algorithms

• Concept of Threads: User level & Kernel level Threads Thread Scheduling;

• Multiprocessor/Multi core Processor Scheduling.

• Case Studies of Process Management in Unix/Linux& Windows;

• System Calls used in these Operating Systems for Process Management.

• Concurrency & Synchronization:Real and Virtual Concurrency

• Mutual Exclusion Synchronization

• Critical Section Problem Solution to Critical Section Problem: Mutex Locks;

• Monitors;

• SemaphoresWAIT/SIGNAL operations and their implementation;

• Classical Problems of Synchronization;

• Inter-Process Communication.

• Deadlocks:Deadlock Characterization Prevention Avoidance Recovery.

UNIT-4 : Memory Management

• Different Memory Management Techniques –Contiguous allocation;

• Non-contiguous allocation: Paging Segmentation Paged Segmentation;

• Comparison of these techniques.

• Virtual Memory – Concept Overlay Dynamic Linking and Loading

• Implementation of Virtual Memory by Demand Paging etc.;

• Memory Management in Unix/Linux& Windows.

UNIT-5 : Input / Output Management

• Overview of Mass Storage Structures Disk Scheduling;

• I/O Systems: Different I/O Operations- Program Controlled

• Interrupt Driven Concurrent I/O Synchronous/Asynchronous and Blocking/Non-Blocking I/O Operations

• I/O BufferingApplication I/O Interface Kernel I/O Subsystem

• Transforming I/O requests to hardware operations.

• Overview of Protection & Security Issues and Mechanisms;

• Introduction to Multiprocessor Real Time Embedded and Mobile Operating Systems;

• Overview of Virtualization.

== END OF UNITS==

Syllabus of AL-502 Database Management Systems

Source: (rgpv.ac.in)

UNIT-1 :

• :DBMS Concepts and architecture Introduction

• Database approach v/s Traditional file accessing approach Advantages of database systems

• Data models Schemes and instances

• Data independence Data Base Language and interfaces

• Overall Database Structure

• Functions of DBA and designer

• ER data model: Entitles and attributes Entity types Defining the E-R diagram

• Concept of Generalization Aggregation and Specialization.

• Transforming ER diagram into the tables.

• Various other data models object oriented data Model Network data model and Relational data model

• Comparison between the three types of models.

• Storage structures: Secondary Storage Devices

• Hashing & Indexing structures: Single level & multilevel indices.

UNIT-2 :

• Relational Data models: Domains Tuples Attributes Relations Characteristics of relations

• Keys Key attributes of relation

• Relational database Schemes Integrity constraints.

• Referential integrity Intension and Extension

• Relational Query languages: SQLDDL DML integrity constraints Complex queries various joins

• indexing triggers assertions Relational algebra and relational calculus

• Relational algebra operations like select Project Join Division outer union.

• Types of relational calculus i.e. Tuple oriented and domain oriented relational calculus and its operations.

UNIT-3 :

• Data Base Design: Introduction to normalization

• Normal forms- 1NF 2NF 3NF and BCNF

• Functional dependencyDecomposition Dependency preservation and lossless join

• problems with null valued and dangling tuples multi valued dependencies.

• Query Optimization: Introduction steps of optimization

• various algorithms to implement select

• project and join operations of relational algebra

• optimization methods: heuristic based cost estimation based.

UNIT-4 :

• Transaction Processing Concepts: -Transaction System

• Testing of Serializability Serializability of schedules conflict & view serializable schedule recoverability

• Recovery from transaction failures.

• Log based recovery. Checkpoints deadlock handling.

• Concurrency Control Techniques: Concurrency Control locking Techniques for concurrency control timestamping protocols for concurrency control

• validation based protocol multiple granularity.

• Multi version schemes Recovery with concurrent transaction. Introduction to Distributed databases data mining data warehousing

• Object Technology and DBMS Comparative study of OODBMS Vs DBMS .

• Temporal Deductive Multimedia Web & Mobile database. .

UNIT-5 :

• Case Study of Relational Database Management Systems through Oracle/PostgreSQL /MySQL: Architecture physical files

• memory structures background process.

• Data dictionary dynamic performance view.

• Security role management privilege management profiles invoke defined security model.

• SQL queries Hierarchical quires inline queries flashback queries.

• Introduction of ANSI SQL

• Cursor management: nested and parameterized cursors.

• Stored procedures usage of parameters in procedures.

• User defined functions their limitations. Triggers mutating errors instead of triggers.

== END OF UNITS==

Syllabus of AL-503 (A) Information Retrieval (Departmental Elective)

Source: (rgpv.ac.in)

UNIT-1 :

• Introduction – History of IR- Components of IR –

• Issues -Open source Search engine Frameworks –

• The Impact of the web on IR –

• The role of artificial intelligence (AI) in IR – IR Versus Web Search –

• Components of a search engine

• Characterizing the web.

UNIT-2 :

• Boolean and Vector space retrieval models-

• Term weighting – TF-IDF weighting cosine similarity –

• Pre processing – Inverted indices –

• efficient processing with sparse vectors Language Model based IR –

• Probabilistic IR -Latent Semantic indexing – Relevance feedback and query expansion

UNIT-3 :

• Web search overview

• web structure the user paid placement search engine optimization

• Web Search Architectures – crawling – meta-crawlers

• Focused Crawling – web indexes – Near duplicate detection – Index Compression – XML retrieval.

UNIT-4 :

• Link Analysis -hubs and authorities – Page Rank and HITS algorithms –

• Searching and Ranking -Relevance Scoring and ranking for Web –

• Similarity – Hadoop & Map Reduce –

• Evaluation -Personalized search –

• Collaborative filtering and content-based recommendation of documents And products – handling invisible Web –

• Snippet generation Summarization.

• Question Answering Cross-Lingual Retrieval.

UNIT-5 :

• Information filtering: organization and relevance feedback – Text Mining- Text classification and clustering –

• Categorization algorithms naive Bayes

• decision trees and nearest neighbor –

• Clustering algorithms: agglomerative clustering

• k-means expectation maximization (EM).

== END OF UNITS==

Syllabus of AL-503 (B) Deep Learning (Departmental Elective)

Source: (rgpv.ac.in)

UNIT-1 :

• Introduction History of Deep Learning

• McCulloch Pitts Neuron

• Multilayer Perceptions (MLPs) Representation Power of MLPs

• Sigmoid Neurons Feed Forward Neural Networks

• Back propagation weight initialization methods

• Batch Normalization Representation Learning

• GPU implementation Decomposition – PCA and SVD.

UNIT-2 :

• Deep Feedforward Neural Networks

• Gradient Descent (GD) Momentum Based GD Nesterov Accelerated GD Stochastic GD

• AdaGrad Adam RMSProp

• Auto-encoder Regularization in auto-encoders Denoising auto-encoders Sparse auto-encoders

• Contractive auto-encodersVariational auto-encoder

• Auto-encoders relationship with PCA and SVD

• Dataset augmentation.

• Denoising auto encoders

UNIT-3 :

• Introduction to Convolutional neural Networks (CNN) and its architectures

• CCN terminologies: ReLu activation function Stride padding pooling convolutions operations

• Convolutional kernels types of layers: Convolutional pooling fully connected Visualizing CNN

• CNN examples: LeNet AlexNet ZF-Net VGGNet GoogLeNet ResNet RCNNetc.

• Deep Dream Deep Art.

• Regularization: Dropout drop Connect unit pruning stochastic pooling

• artificial data injecting noise in input early stopping

• Limit Number of parameters Weight decay etc.

UNIT-4 :

• Introduction to Deep Recurrent Neural Networks and its architectures

• Back propagation Through Time (BPTT)

• Vanishing and Exploding Gradients

• Truncated BPTT Gated Recurrent Units (GRUs)

• Long Short Term Memory (LSTM)

• Solving the vanishing gradient problem with LSTMs

• Encoding and decoding in RNN network

• Attention Mechanism Attention over images Hierarchical Attention

• Directed Graphical Models.

• Applications of Deep RNN in Image Processing

• Natural Language Processing Speech recognition Video Analytics.

UNIT-5 :

• Introduction to Deep Generative Models

• Restricted Boltzmann Machines (RBMs) Gibbs Sampling for training RBMs

• Deep belief networks Markov Networks Markov Chains

• Auto-regressive Models: NADE MADE PixelRNN

• Generative Adversarial Networks (GANs)

• Applications of Deep Learning in Object detection

• speech/ image recognition video analysis NLP medical science etc.

== END OF UNITS==

Syllabus of AL-503(C) Optimization Techniques in Machine Leaning (Departmental Elective)

Source: (rgpv.ac.in)

UNIT-1 :

• Introduction What is optimization

• Formulation of LPP Solution of LPP: Simplex method

• Basic Calculus for optimization: Limits and multivariate functions

• Derivatives and linear approximations: Single variate functions and multivariate functions.

UNIT- 2 :

• Machine Learning Strategy ML readiness

• Risk mitigation

• Experimental mindset Build/buy/partner setting up a team

• Understanding and communicating change

UNIT-3 :

• Responsible Machine Learning AI for good and all

• Positive feedback loops and negative feedback loops

• Metric design and observing behaviours

• Secondary effects of optimization

• Regulatory concerns.

UNIT-4 :

• Machine Learning in production and planning Integrating info systems

• users break things time and space complexity in production

• when to retain the model?

• Logging ML model versioning

• Knowledge transfer

• Reporting performance to stakeholders.

UNIT-5 :

• Care and feeding of your machine learning model MLPL Recap

• Post deployment challenges

• QUAM monitoring and logging QUAM Testing QUAM maintenance QUAM updating

• Separating Data stack from Production

• Dashboard Essentials and Metrics monitoring.

== END OF UNITS==

Syllabus of AL-504 (A) AI in Health Care (Open Elective)

Source: (rgpv.ac.in)

UNIT-1 :

• Disease detection with computer vision Medical Image Diagnosis

• Eye Disease and Cancer Diagnosis

• Building and Training a Model for Medical Diagnosis

• Training prediction and loss

• Image Classification and Class Imbalance

• Generating More Samples Model Testing

UNIT-2 :

• Evaluating models Sensitivity

• Specificity and Evaluation Metrics

• Accuracy in terms of conditional probability

• Confusion matrix ROC curve and Threshold Image segmentation on MRI images Medical Image Segmentation MRI Data and Image Registration

• Segmentation 2-D U-Net and 3-D U-Net Data augmentation and loss function for segmentation

• Different Populations and Diagnostic Technology External validation.

UNIT-3 :

• Linear prognostic models Medical Prognosis

• Atrial fibrillation Liver Disease Mortality Risk of heart disease

• Evaluating Prognostic Models

• Concordant Pairs Risk Ties Permissible Pairs.

• Prognosis with Tree-based models Decision trees for prognosis fix over fitting

• Different distributionsMissing Data example Imputation

UNIT-4 :

• Survival Models and Time Survival Model

• Survival function collecting time data estimating the survival function.

• Build a risk model using linear and tree-based models Hazard Functions

• Relative risk Individual vs. baseline hazard

• Survival Trees

• Nelson Aalen estimator

UNIT-5 :

• Medical Treatment Effect Estimation Analyze data from a randomized control trial

• Average treatment effect Conditional average treatment effect

• T-Learner S-Learner C-for benefit.

== END OF UNITS==

Syllabus of AL-504 (B) Natural Language Processing (Open Elective)

Source: (rgpv.ac.in)

UNIT-1 : Introduction

• Origins and challenges of NLP – Language Modeling: Grammar based LM

• Statistical LM – Regular Expressions

• Finite-State Auto mat – English Morphology

• Transducers for lexicon and rules

• Tokenization Detecting and Correcting Spelling Errors

• Minimum Edit Distance.

UNIT-2 : Word Level Analysis

• Un-smoothed N-grams Evaluating N-grams

• Smoothing

• Interpolation and Back off – Word Classes Part-of-Speech Tagging

• Rule-based Stochastic and Transformation-based tagging

• Issues in PoS tagging – Hidden Markov and Maximum Entropy models

• Viterbi algorithms and EM training

UNIT-3 : Syntactic Analysis

• Context-Free Grammars Grammar rules for English

• Treebanks Normal Forms for grammar – Dependency Grammar – Syntactic Parsing Ambiguity

• Dynamic Programming parsing – Shallow parsing – Probabilistic CFG

• Probabilistic CYK Probabilistic Lexicalized CFGs – Feature structures

• Unification of feature structures.

UNIT-4 : Semantics and Pragmatics

• Requirements for representation

• First-Order Logic Description Logics – Syntax-Driven Semantic analysis

• Semantic attachments – Word Senses Relations between Senses

• Thematic Roles selectional restrictions – Word Sense Disambiguation

• WSD using Supervised Dictionary & Thesaurus

• Bootstrapping methods – Word Similarity using Thesaurus and Distributional methods.

• Compositional semantics.

UNIT-5 : Application of NLP

• intelligent work processors: Machine translation

• user interfaces

• Man-Machine interfaces

• natural language querying tutoring and authoring systems

• speech recognition and commercial use of NLP.

== END OF UNITS==

Syllabus of AL-504 (C) Computational Intelligence (Open Elective)

Source: (rgpv.ac.in)

UNIT-1 :

• Introduction to Computational Intelligence (CI): Basics of CI History of CI

• Adaptation Learning Self-Organization State Space Search and Evolution

• CI and Soft Computing CI Techniques; Applications of CI;

• Decision Trees: Introduction Evaluation Different splitting criterion

• Implementation aspect of decision tree.

• Neural Network: Introduction types issues implementation applications

UNIT-2 :

• Fuzzy Set Theory: Fuzzy Sets Fuzzy Set Characteristics

• Basic Definition and Terminology Fuzzy OperatorsFuzzy Relations and Composition

• Member Function Formulation Fuzzy Rules and Fuzzy Reasoning

• Extension Fuzzy Inference Systems

• Input Space Partitioning and Fuzzy Modeling.

• Fuzziness and Defuzzification Fuzzy Controllers

• Different Fuzzy Models: Mamdani Fuzzy Models Sugeno Fuzzy Models

• Tsukamoto Fuzzy Models etc.

• Neuro Fuzzy Modeling

• Introduction to Neuro Fuzzy Control

UNIT-3 :

• Rough Set Theory: Introduction Fundamental Concepts

• Knowledge Representation Set Approximations and Accuracy

• Vagueness and Uncertainty in Rough Sets

• Rough Membership Function Attributes Dependency and Reduction

• Application Domain Hidden Markov Model (HMM)

• Graphical Models Variable Elimination Belief Propagation

• Markov Decision Processes.

UNIT-4 :

• Evolutionary Computation: Genetic Algorithms: Basic Genetics Concepts Working Principle Creation of Off springs

• Encoding Fitness Function Selection Functions

• Genetic Operators-Reproduction Crossover Mutation;

• Genetic Modeling Benefits;

• Problem Solving;

• Introduction to Genetic Programming

• Evolutionary Programming and Evolutionary Strategies.

UNIT-5 :

• Swarm Intelligence: Introduction to Swarm Intelligence

• Swarm Intelligence Techniques: Ant Colony Optimization (ACO): Overview ACO Algorithm;

• Particle Swarm Optimization (PSO): Basics Social Network Structures PSO Parameters and Algorithm;

• Grey wolf optimization(GWO);

• Application Domain of ACO and PSO;

• Bee Colony Optimization etc.;

• Hybrid CI Techniques and applications;

• CI Tools

== END OF UNITS==

==End of Syllabus==