RTMNU TY AI & DS syllabus

RTMNU · Third Year B.Tech Artificial Intelligence & Data Science · NEP 2020

Data Handling and Visualization

BMD5T20 · Semester V · 2 credits · College 30 + university 70

A 2-credit multidisciplinary-minor (MDM-III) course of the programme.

  1. Unit 1: Data Handling

    8 hours

    Applications of data analytics in science and engineering, examples of supervised, unsupervised and reinforcement learning, variable types and terminology, and data analytics in cloud computing.

    Examined in the 70-mark end-semester paper

    • Types of learning
    • Types of data and measurement scales
    • Data science, ML and AI compared
  2. Unit 2: Data Collection and Storage Techniques

    6 hours

    Collecting software-engineering data by direct and indirect involvement of engineers and by studying work artefacts; cloud storage, software-defined storage, and file, block and object storage.

    Examined in the 70-mark end-semester paper

    • Data collection in software engineering: direct, indirect and artefact studies
    • Data collection strategies
    • Cloud storage
    • Storage types: file, block, object and software-defined storage
  3. Unit 3: Data Visualization and Data Cleaning Techniques

    7 hours

    Histograms, box plots, scatter plots and pixel-based techniques, quality metrics for data presentation; filtering, missing data, duplicates and outliers, scaling and normalisation.

    Examined in the 70-mark end-semester paper

    • Plotting with pandas: line, bar, scatter, histogram and heat map
    • Higher-dimensional displays
    • Handling missing data
    • Outlier detection: z-score and IQR
    • Normalisation and standardisation
  4. Unit 4: Functionalities of Data Storage Management

    7 hours

    Data availability, easy and quick access, automatic tiering, backup solutions, encryption of data in transit and at rest, multifactor authentication against unauthorised access, and control and compliance.

    Examined in the 70-mark end-semester paper

    • Storage tiering, availability and access control
    • Disaster recovery, backup and high availability
    • Symmetric and asymmetric encryption
    • Identity and access management in the cloud
    • Data governance
  5. Unit 5: Model Assessment and Selection

    8 hours

    Statistical decision theory for regression and classification, training and test errors, regularisation and stability, the bias–variance trade-off, optimism of the training error rate, estimates of in-sample prediction error and the Bayesian information criterion.

    Examined in the 70-mark end-semester paper

    • Statistical decision theory for regression and classification
    • Bias-variance trade-off
    • Ridge and lasso regularisation
    • Training error optimism and in-sample prediction error
    • Model selection measures

Unit contents are summarised from the official RTMNU syllabus . AiCanCode.org is not affiliated with Rashtrasant Tukadoji Maharaj Nagpur University (RTMNU).