SGBAU TY AI & DS syllabus

SGBAU · Third Year B.E. Artificial Intelligence and Data Science · NEP 2020

Data Science

5AD222PC · Semester V · 3 credits · IE 40 + ESE 60

  1. Unit 1: Data Science and Types of Data

    8 hours

    The definition and scope of data science, types of data and measurement scales, statistics and data sources, population and sample; qualitative and quantitative, nominal and ordinal, cross-sectional and time-series, discrete and continuous data; nominal, ordinal, interval and ratio scales; structured and unstructured data — text, image, audio and video.

    Examined in the 60-mark end-semester paper

    • Data science, ML and AI compared
    • Types of data and measurement scales
    • Statistics in data science and types of data
    • Population, sample and sampling methods
  2. Unit 2: Data Acquisition, Wrangling and Exploration

    8 hours

    Data acquisition, wrangling, cleaning and exploration, preprocessing and transformation, exploratory data analysis, tabulation and frequency distributions, histograms, pie, bar and Pareto charts, scatter and line plots, box plots, heat maps, correlation-matrix visualisation and dashboards.

    Examined in the 60-mark end-semester paper

    • Data integration and transformation
    • Handling missing data
    • Exploratory data analysis
    • Principles of data visualisation
    • Matplotlib and Seaborn
  3. Unit 3: Mathematical Foundations of Data Science

    6 hours

    Linear algebra, statistics and optimisation for data science; matrices and their properties — determinants, trace, rank and nullity — eigenvalues and eigenvectors, matrix factorisations, inner products, distance measures, projections, hyperplanes and half-planes.

    Examined in the 60-mark end-semester paper

    • Vectors and matrices for data science
    • Eigenvalues and eigenvectors
    • Orthogonal projections and least squares
    • Distance measures: Euclidean, Manhattan, Minkowski and Hamming
  4. Unit 4: Optimisation

    6 hours

    Unconstrained optimisation and the conditions for optima, gradient-descent methods, constrained optimisation and the KKT conditions, non-gradient techniques, least-squares optimisation and the optimisation view of machine learning.

    Examined in the 60-mark end-semester paper

    • Convex and quadratic programming
    • Gradient descent variants
    • Optimisation in data science: KKT conditions and least squares
  5. Unit 5: Probability Distributions and Point Estimation

    6 hours

    Common probability distributions, sampling and sampling distributions, point estimation and the properties of estimators, maximum-likelihood estimation and its large-sample properties, the method of moments, least squares and minimum chi-square.

    Examined in the 60-mark end-semester paper

    • Probability and Bayes' theorem
    • Sampling distributions
    • Point, interval and Bayesian estimation
    • Method of moments and maximum likelihood
  6. Unit 6: Interval Estimation and Hypothesis Testing

    6 hours

    Confidence intervals and their duality with tests, intervals for one and two population parameters, sample size; one-sample tests of means, proportions and variances, the Neyman–Pearson lemma and likelihood-ratio tests.

    Examined in the 60-mark end-semester paper

    • Hypothesis tests, significance and confidence intervals
    • Sampling and sample size
    • Z-tests for means and proportions
    • Variance tests: chi-square and F
    • Neyman-Pearson lemma
    • Likelihood ratio test

Unit contents are summarised from the official SGBAU syllabus . AiCanCode.org is not affiliated with Sant Gadge Baba Amravati University (SGBAU).