AI & Machine LearningSemester 2-2 syllabus

This semester marks the shift into the AI&ML specialization proper, introducing Machine Learning and Database Management Systems as core subjects alongside the mathematical grounding of Optimization Techniques and Probability & Statistics. Digital Logic & Computer Organization supplies systems-level understanding, while two labs give students hands-on ML and SQL practice. Full Stack Development-1 and Design Thinking & Innovation add practical web-development and ideation skills.

Subjects

Optimization Techniques

(Management Course-I)

• Unit 1: Formulating optimization problems and classical techniques for single- and multi-variable optimization, including Lagrange multipliers and Kuhn-Tucker conditions.
• Unit 2: Linear programming — standard form, geometric interpretation, and the simplex algorithm.
• Unit 3: The transportation problem, including initial feasible solutions and optimality testing.
• Unit 4: Nonlinear programming for constrained and unconstrained cases, covering search methods and penalty-function approaches.
• Unit 5: Dynamic programming — multistage decision processes and the principle of optimality.

L-T-P: 2-0-0, 2 credits

Probability & Statistics

• Unit 1: Descriptive statistics for data science — central tendency, variability, skewness, and kurtosis.
• Unit 2: Correlation and regression, including linear, multiple, and curvilinear regression.
• Unit 3: Probability theory and standard discrete/continuous distributions (binomial, Poisson, normal).
• Unit 4: Sampling theory — sampling distributions, estimation, and the central limit theorem.
• Unit 5: Hypothesis testing — significance levels, error types, and tests for large and small samples.

L-T-P: 3-0-0, 3 credits

Machine Learning

• Unit 1: Introduction to machine learning — its evolution, learning paradigms, and the typical ML pipeline from data acquisition to model evaluation.
• Unit 2: Nearest-neighbour models — proximity measures, KNN classification and regression, and classifier performance evaluation.
• Unit 3: Decision-tree-based models and the Bayes classifier, including Naive Bayes and impurity measures.
• Unit 4: Linear discriminants — perceptrons, support vector machines, logistic regression, and multi-layer perceptrons trained via backpropagation.
• Unit 5: Clustering techniques — K-means, fuzzy C-means, rough clustering, expectation-maximization, and spectral clustering.

L-T-P: 3-0-0, 3 credits

Database Management Systems

• Unit 1: Database fundamentals, data models, schema architecture, and entity-relationship modelling.
• Unit 2: The relational model, constraints, relational algebra/calculus, and basic SQL DDL/DML.
• Unit 3: Advanced SQL querying — joins, nested queries, aggregation, and views.
• Unit 4: Normalization theory from 1NF through BCNF, 4NF, and 5NF.
• Unit 5: Transaction management — ACID properties, concurrency control, recovery, and indexing techniques including B+ trees and hashing.

L-T-P: 3-0-0, 3 credits

Digital Logic & Computer Organization

• Unit 1: Data representation and combinational logic circuits, including K-map minimization.
• Unit 2: Sequential circuits and the basic structural organization of a computer.
• Unit 3: Computer arithmetic and processor organization, including instruction execution and control unit design.
• Unit 4: Memory hierarchy — RAM, ROM, cache, and virtual memory considerations.
• Unit 5: I/O organization — interrupts, DMA, buses, and standard I/O interfaces.

L-T-P: 3-0-0, 3 credits

Machine Learning Lab

• Computing central tendency/dispersion measures and applying preprocessing techniques (attribute selection, missing-value handling, discretization, outlier removal).
• Implementing KNN, decision trees, and random forests for classification and regression.
• Applying Naive Bayes, support vector machines, and both simple linear and logistic regression.
• Building multi-layer perceptron classifiers.
• Implementing K-means, fuzzy C-means, and expectation-maximization clustering.

L-T-P: 0-0-3, 1.5 credits

Database Management Systems Lab

• DDL/DML/DCL practice — table creation, constraints, and basic queries.
• Nested queries, aggregate functions, grouping, and view management.
• PL/SQL programming — control structures, conversion/string/date functions.
• Building procedures, functions, cursors, and triggers.
• Database connectivity exercises using ODBC/JDBC.

L-T-P: 0-0-3, 1.5 credits

Full Stack Development-1

(Skill Enhancement Course)

• HTML fundamentals — lists, links, images, tables, forms, and frames.
• CSS styling — selector types, the box model, and color/font/text properties.
• JavaScript basics — input/output, type conversion, conditional statements, and loops.
• Working with predefined and user-defined JavaScript objects, functions, and events.
• An introduction to Node.js as a bridge toward server-side scripting.

L-T-P: 0-1-2, 2 credits

Design Thinking & Innovation

• Unit 1: Introduction to design thinking and its fundamental components and principles.
• Unit 2: The design thinking process from empathy through ideation.
• Unit 3: Innovation as a discipline and its role in product and service development.
• Unit 4: Product design, including specification-setting and prototyping activities.
• Unit 5: Applying design thinking to business processes.

L-T-P: 1-0-2, 2 credits

Semester total: 15-1-12 contact hours, 21 credits, continuing the mandatory community service project internship theme from the prior semester.