Mumbai University BE Electrical syllabus

Mumbai University · Final Year Electrical Engineering · Rev-2019 'C' Scheme

Artificial Intelligence and Machine Learning

EEDO7023 · Department Optional Course 4 · Semester VII · 3 credits · Internal tests 20 (average of two) + end-semester 80

End-semester paper (3 hours): Six questions of 20 marks; Q1 is compulsory and you answer four.

One of the Department Optional Course 4 options.

All notes for this subject
  1. Module 1: Introduction to AI

    4 hours

    Application areas; state-space search: depth-first and breadth-first; heuristic search: best-first, hill climbing and beam search.

    Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then

    • AI versus machine learning
    • Depth-first and breadth-first search
    • Hill climbing
    • A* and best-first search
  2. Module 2: Artificial Neural Networks

    8 hours

    Biological and artificial neurons; activation functions; perceptrons and their power; gradient descent and the delta rule; multilayer networks and backpropagation; convergence, generalisation, overfitting and stopping.

    Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then

    • Perceptron and the delta rule
    • Multilayer networks and backpropagation
    • Overfitting and stopping criteria
  3. Module 3: Introduction to Machine Learning

    3 hours

    Learning problems; data representation; structured and unstructured data; forms of learning; ML and data mining; linear algebra for ML.

    Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then

    • Forms of learning and data representation
  4. Module 4: Supervised and Statistical Learning

    10 hours

    Bias and variance; regression and classification metrics; Bayesian reasoning; k-NN; discriminant and regression functions; least-squares and logistic regression; SVR; decision trees; regularisation.

    Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then

    • Bias and variance
    • Regression and classification metrics
    • K-nearest neighbours
    • Least squares regression
    • Logistic regression
    • Support vector regression and decision trees
  5. Module 5: Clustering and Data Transformation

    8 hours

    K-means; data cleansing; derived and discretised attributes; attribute reduction and PCA; introduction to reinforcement and deep learning.

    Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then

    • K-means and Gaussian mixtures
    • Data cleansing and discretisation
    • Principal component analysis
    • Introduction to reinforcement and deep learning
  6. Module 6: AI and ML in Electrical Engineering

    6 hours

    Voltage control, protection, security assessment, condition monitoring and maintenance scheduling; load forecasting, voltage stability, demand-side management, load patterns and wind forecasting.

    Examined in the 80-mark end-semester paper; the class tests cover what has been taught by then

    • AI applications in power systems
    • Load and wind speed forecasting with ML

Module contents are summarised from the official Mumbai University syllabus . AiCanCode.org is not affiliated with the University of Mumbai.