AIML 5th Semester Syllabus

Unit 1Introduction to Operating Systems

Function, Evolution, Different types of Operating Systems, Desirable Characteristics and features of an OS · 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 issues · Operating System Structures

Unit 2File Systems (Secondary Storage Management)

File concept and the view of users versus system programmers · Hard‑disk organization, disk formatting and file‑system creation · 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 used in Unix/Linux and Windows · System calls used for file management

Unit 3Process Management

Concept of a process and the process‑state diagram · Different types of schedulers and CPU‑scheduling algorithms; evaluation of scheduling algorithms · Threads – user‑level and kernel‑level, thread scheduling, multiprocessor/multicore scheduling · Case studies of process management in Unix/Linux and Windows; related system calls · Concurrency and synchronization – real/virtual concurrency, mutual exclusion, critical‑section problem, mutex locks, monitors, semaphores, WAIT/SIGNAL operations, classic synchronization problems, inter‑process communication · Deadlocks – characterization, prevention, avoidance, recovery

Unit 4Memory Management

Memory‑management techniques – contiguous allocation; non‑contiguous allocation (paging, segmentation, paged segmentation); comparative analysis · Virtual memory – concept, overlay, dynamic linking and loading, implementation by demand paging · Memory management approaches in Unix/Linux and Windows

Unit 5Input/Output Management

Mass‑storage structures and disk scheduling · I/O system models – program‑controlled, interrupt‑driven, concurrent I/O; synchronous/asynchronous and blocking/non‑blocking operations; I/O buffering; application I/O interface; kernel I/O subsystem; translation of I/O requests to hardware operations · Protection and security issues and mechanisms · Introduction to multiprocessor, real‑time, embedded and mobile operating systems · Overview of virtualization

Unit 1DBMS Concepts and Architecture

Introduction to DBMS concepts and architecture · Database approach vs. traditional file accessing approach · Advantages of database systems · Data models, schemas and instances · Data independence · Database languages and interfaces · Overall database structure · Functions of DBA and designer · Entity‑Relationship (ER) data model: entities, attributes, entity types · Defining the ER diagram · Generalization, aggregation and specialization in ER modeling · Transforming ER diagram into relational tables · Other data models: object‑oriented, network, relational · Comparison of data‑model types · Storage structures: secondary storage devices · Hashing and indexing structures: single‑level and multilevel indices

Unit 2Relational Data Models

Relational data model fundamentals: domains, tuples, attributes, relations · Characteristics of relations and keys (primary, candidate, foreign) · Relational database schemas and integrity constraints · Referential integrity, intension and extension · SQL Data Definition Language (DDL) and Data Manipulation Language (DML) · Integrity constraints in SQL · Complex SQL queries and various join operations · Indexing and triggers in relational databases · Assertions in SQL · Relational algebra operations: select, project, join, division, outer union · Relational calculus: tuple‑oriented and domain‑oriented forms

Unit 3Database Design and Query Optimization

Normalization theory and techniques · Normal forms: 1NF, 2NF, 3NF, BCNF · Functional dependencies and decomposition · Dependency preservation and lossless‑join decomposition · Handling null‑valued and dangling tuples · Multivalued dependencies · Introduction to query optimization · Steps of query optimization · Algorithms for implementing select, project, and join operations · Heuristic‑based and cost‑estimation‑based optimization methods

Unit 4Transaction Processing and Concurrency Control

Transaction concepts and transaction system · Serializability testing: conflict‑serializable and view‑serializable schedules · Recoverability and recovery from transaction failures · Log‑based recovery, checkpoints, deadlock handling · Concurrency control techniques: locking protocols, timestamp protocols, validation protocols · Multiple‑granularity locking and multiversion concurrency control · Recovery in concurrent transaction environments · Introduction to distributed databases · Data mining and data warehousing basics · Object‑oriented databases vs. traditional DBMS · Comparative study of OODBMS and DBMS · Temporal, deductive, multimedia, web and mobile databases

Unit 5Case Study of Relational DBMS (Oracle/PostgreSQL/MySQL)

Architecture of major RDBMS (Oracle, PostgreSQL, MySQL) · Physical file organization and memory structures · Background processes in RDBMS · Data dictionary and dynamic performance views · Security, role management, privilege management, profiles · Invoker‑defined security model · Advanced SQL queries: hierarchical, inline, flashback · ANSI SQL standards and extensions · Cursor management: nested and parameterized cursors · Stored procedures and usage of parameters · User‑defined functions and their limitations · Triggers, mutating table errors, instead‑of triggers

Unit 1Introduction

History of IR · Components of IR · Issues in IR · Open‑source search‑engine frameworks · Impact of the Web on IR · Role of artificial intelligence (AI) in IR · IR versus Web search · Components of a search engine · Characterizing the Web

Unit 2Boolean and Vector Space Retrieval Models

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 (LSI) · Relevance feedback and query expansion

Unit 3Web Search Overview

Web search overview · Web structure and user‑paid placement search‑engine optimization · Web‑search architectures · Crawling · Meta‑crawlers · Focused crawling · Web indexes · Near‑duplicate detection · Index compression · XML retrieval

Unit 4Link Analysis

Link analysis · Hubs and authorities · PageRank and HITS algorithms · Searching and ranking · Relevance scoring and ranking for the Web · Similarity measures · Hadoop & MapReduce evaluation · Personalized search · Collaborative filtering and content‑based recommendation of documents and products · Handling the invisible Web · Snippet generation and summarization · Question answering · Cross‑lingual retrieval

Unit 5Information Filtering

Information filtering: organization and relevance feedback · Text mining · Text classification and clustering · Categorization algorithms: naive Bayes, decision trees, nearest‑neighbor · Clustering algorithms: agglomerative clustering, k‑means, expectation‑maximization (EM)

Unit 1Introduction

Introduction and History of Deep Learning · McCulloch–Pitts neuron model · Multilayer Perceptrons (MLPs) · Representation power of MLPs · Sigmoid neurons · Feed‑forward neural networks · Back‑propagation algorithm · Weight initialization methods · Batch normalization · Representation learning · GPU implementation of neural networks · Dimensionality reduction – Principal Component Analysis (PCA) and Singular Value Decomposition (SVD)

Unit 2Deep Feed‑Forward Networks and Optimization

Deep feed‑forward neural networks · Gradient Descent (GD) · Momentum‑based GD · Nesterov accelerated GD · Stochastic GD · AdaGrad optimizer · Adam optimizer · RMSProp optimizer · Auto‑encoders · Regularization in auto‑encoders · Denoising auto‑encoders · Sparse auto‑encoders · Contractive auto‑encoders · Variational auto‑encoder (VAE) · Relationship between auto‑encoders and PCA/SVD · Dataset augmentation techniques

Unit 3Convolutional Neural Networks

Introduction to Convolutional Neural Networks (CNN) and architectures · Convolutional terminology – ReLU activation, stride, padding, pooling, convolution operations · Convolutional kernels · Layer types – convolutional, pooling, fully‑connected · Visualization of CNNs · Canonical CNN models – LeNet, AlexNet, ZF‑Net, VGGNet, GoogLeNet, ResNet, R‑CNN · Deep Dream and Deep Art applications · Regularization techniques – dropout, drop‑connect, unit pruning, stochastic pooling, artificial data injection, early stopping, weight decay, limiting the number of parameters

Unit 4Recurrent Neural Networks

Introduction to deep Recurrent Neural Networks (RNN) and architectures · Back‑Propagation Through Time (BPTT) · Vanishing and exploding gradient problems · Truncated BPTT · Gated Recurrent Units (GRUs) · Long Short‑Term Memory (LSTM) networks · Mitigating vanishing gradients with LSTMs · Encoder–decoder frameworks for RNNs · Attention mechanisms – standard attention, visual attention, hierarchical attention · Directed graphical models · Applications of deep RNNs in image processing, natural language processing, speech recognition, and video analytics

Unit 5Generative Models

Introduction to deep generative models · Restricted Boltzmann Machines (RBMs) and Gibbs sampling · Deep belief networks · Markov networks and Markov chains · Autoregressive models – NADE, MADE, PixelRNN · Generative Adversarial Networks (GANs) · Applications of deep generative models in object detection, speech and image recognition, video analysis, NLP, and medical science

Unit 1Introduction

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 2Machine Learning Strategy

ML readiness · Risk mitigation · Experimental mindset · Build / buy / partner · Setting up a team · Understanding and communicating change

Unit 3Responsible 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 4Machine Learning in Production and Planning

Integrating information 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 5Care and Feeding of Your Machine Learning Model

MLPL recap · Post‑deployment challenges · QUAM monitoring and logging · QUAM testing · QUAM maintenance · QUAM updating · Separating datastack from production · Dashboard essentials and metrics monitoring

Unit 1Disease detection with computer vision

Medical image diagnosis · Eye disease diagnosis · Cancer diagnosis using imaging · Building and training a model for medical diagnosis · Training, prediction, and loss functions · Image classification and class imbalance handling · Generating additional samples for training (data augmentation) · Model testing and validation

Unit 2Evaluating models

Sensitivity and specificity as evaluation metrics · Accuracy expressed as conditional probability · Confusion matrix construction and interpretation · Receiver operating characteristic (ROC) curve analysis · Threshold selection for classification decisions · Image segmentation on MRI images · Medical image segmentation techniques · MRI data acquisition and image registration · Segmentation algorithms · 2D U‑Net architecture · 3D U‑Net architecture · Data augmentation strategies for segmentation · Loss functions specific to segmentation tasks · Assessment across different populations and diagnostic technologies · External validation of segmentation models

Unit 3Linear prognostic models

Medical prognosis fundamentals · Atrial fibrillation risk modeling · Liver disease mortality prediction · Risk assessment for heart disease · Evaluation of prognostic models · Concordant pair analysis · Risk tie handling · Permissible pair identification · Tree‑based prognostic modeling · Decision trees applied to prognosis · Techniques to mitigate overfitting in trees · Modeling with different statistical distributions · Missing data handling in prognostic datasets · Imputation methods for missing values

Unit 4Survival Models and Time

Survival analysis concepts · Survival function definition · Collection of time‑to‑event data · Estimation of the survival function · Risk modeling using linear models · Risk modeling using tree‑based models · Hazard function formulation · Relative risk estimation · Individual versus baseline hazard comparison · Survival trees methodology · Nelson‑Aalen estimator for cumulative hazard

Unit 5Medical Treatment Effect Estimation

Analysis of randomized controlled trial data · Average treatment effect (ATE) estimation · Conditional average treatment effect (CATE) estimation · T‑Learner methodology · S‑Learner methodology · C‑for‑benefit approach

Unit 1Introduction

Origins and challenges of NLP · Language Modeling: Grammar‑based LM, Statistical LM · Regular Expressions and Finite‑State Automata · English Morphology · Transducers for lexicon and rules · Tokenization · Detecting and correcting spelling errors · Minimum edit distance

Unit 2Word Level Analysis

Unsmoothed N‑grams · Evaluating N‑grams · Smoothing, interpolation and backoff · Word classes · Part‑of‑speech tagging (rule‑based, stochastic, transformation‑based) · Issues in PoS tagging · Hidden Markov and maximum‑entropy models · Viterbi algorithm and EM training

Unit 3Syntactic Analysis

Context‑Free Grammars · Grammar rules for English · Treebanks · Normal forms for grammar · Dependency Grammar · Syntactic parsing · Ambiguity handling · Dynamic‑programming parsing · Shallow parsing · Probabilistic CFG · Probabilistic CYK algorithm · Probabilistic lexicalized CFGs · Feature structures · Unification of feature structures

Unit 4Semantics and Pragmatics

Requirements for representation · First‑order logic · Description logics · Syntax‑driven semantic analysis · Semantic attachments · Word senses and relations between senses · Thematic roles and selectional restrictions · Word‑sense disambiguation (supervised, dictionary & thesaurus, bootstrapping methods) · Word similarity using thesaurus and distributional methods · Compositional semantics

Unit 5Application of NLP

Intelligent work processors: machine translation · User interfaces and man‑machine interfaces · Natural language querying · Tutoring and authoring systems · Speech recognition · Commercial use of NLP

Unit 1Introduction to Computational Intelligence (CI)

Basics of Computational Intelligence (CI) · History of CI · Adaptation and Learning · Self‑Organization · State‑space search and Evolution · CI and Soft Computing · CI techniques and applications · Decision Trees: introduction, evaluation, splitting criteria, implementation · Neural Networks: introduction, types, issues, implementation, applications

Unit 2Fuzzy Set Theory

Fuzzy Sets and characteristics · Definitions and terminology of fuzzy sets · Fuzzy operators and relations/composition · Membership function formulation · Fuzzy rules and reasoning · Fuzzy inference systems and input‑space partitioning · Defuzzification methods · Fuzzy controllers · Mamdani, Sugeno, Tsukamoto fuzzy models · Neuro‑fuzzy modeling and neuro‑fuzzy control

Unit 3Rough Set Theory

Rough set fundamentals and knowledge representation · Set approximations, accuracy, vagueness, and uncertainty · Rough membership function · Attribute dependency and reduction · Applications of rough sets · Hidden Markov Models (HMM) · Graphical models, variable elimination, belief propagation · Markov Decision Processes

Unit 4Evolutionary Computation

Genetic Algorithms: basic genetics, concepts, working principle · Chromosome encoding, fitness functions, selection methods · Genetic operators: reproduction, crossover, mutation · Genetic modeling and problem solving · Genetic programming, evolutionary programming, evolutionary strategies

Unit 5Swarm Intelligence

Swarm Intelligence fundamentals · Ant Colony Optimization (ACO): overview and algorithm · Particle Swarm Optimization (PSO): basics, social network structure, parameters, algorithm · Grey Wolf Optimization (GWO) · Bee Colony Optimization · Hybrid CI techniques and applications · CI tools