B.E Artificial Intelligence and Machine Learning Machine Learning Syllabus - Mumbai University
This is the Third Year AI-ML syllabus under REV-2019 'C' Scheme, in force from the academic year 2022-23. The University has not yet published an NEP 2020 syllabus for this year of the degree, and this is the scheme its examinations are set on.
Loading syllabus...
Syllabus for Machine Learning
Module 1: Introduction to Machine Learning
- 1.1 Introduction to Machine Learning, Issues in Machine Learning, Application of Machine Learning, Steps of developing a Machine Learning Application. Supervised and Unsupervised Learning: Concepts of Classification, Clustering and prediction, Training, Testing and validation dataset, cross validation, overfitting and underfitting of model Performance Measures: Measuring Quality of model- Confusion Matrix, Accuracy, Recall, Precision, Specificity, F1 Score, RMSE
Module 2: Mathematical Foundation for ML
- 2.1 System of Linear equations, Norms, Inner products, Length of Vector, Distance between vectors, Orthogonal vectors
- 2.2 Symmetric Positive Definite Matrices, Determinant, Trace, Eigenvalues and vectors, Orthogonal Projections, Diagonalization, SVD and its applications
Module 3: Linear Models
- The least-squares method, Multivariate Linear Regression, Regularized Regression, Using Least-Squares Regression for classification Support Vector Machines
Module 4: Clustering
- 4.1 Hebbian Learning rule
- 4.2 Expectation -Maximization algorithm for clustering
Module 5: Classification models
- Introduction, Fundamental concept, Evolution of Neural Networks, Biological Neuron, Artificial Neural Networks, NN architecture, McCulloch-Pitts Model. Designing a simple network, Non-separable patterns, Perceptron model with Bias. Activation functions, Binary, Bipolar, continuous, Ramp. Limitations of Perceptron. Perceptron Learning Rule. Delta Learning Rule (LMS-Widrow Hoff), Multi-layer perceptron network. Adjusting weights of hidden layers. Error back propagation algorithm. Logistic regression
Module 6: Dimensionality Reduction
- Curse of Dimensionality. Feature Selection and Feature Extraction Dimensionality Reduction Techniques, Principal Component Analysis.
Useful links
- 1 Nathalie Japkowicz & Mohak Shah, ―Evaluating Learning Algorithms: A Classification Perspective‖, Cambridge.
- 2 Marc Peter Deisenroth, Aldo Faisal, Cheng Soon Ong, ―Mathematics for machine learning‖,
- 3 Samir Roy and Chakraborty, ―Introduction to soft computing‖, Pearson Edition.
- 4 Ethem Alpaydın, ―Introduction to Machine Learning‖, MIT Press McGraw-Hill Higher Education
- 5 Peter Flach, ―Machine Learning‖, Cambridge University Press
- 1 Tom M. Mitchell, ―Machine Learning‖, McGraw Hill
- 2 Kevin P. Murphy, ―Machine Learning ― A Probabilistic Perspective‖, MIT Press
- 3 Stephen Marsland, ―Machine Learning an Algorithmic Perspective‖, CRC Press
- 4 Shai Shalev-Shwartz, Shai Ben-David, ―Understanding Machine Learning‖, Cambridge University Press
- 5 Peter Harrington, ―Machine Learning in Action‖, DreamTech Press
- 2 AI and ML Certification - Enroll in PGP AI ML Courses with Purdue (simplilearn.com)
- 3 https://www.learndatasci.com/out/coursera-machine-learning/
- 4 https://www.learndatasci.com/out/google-machine-learning-crash-course/
Reproduced from the University of Mumbai syllabus for B.E. (Artificial Intelligence and Machine Learning) under REV-2019 'C' Scheme, in force from the academic year 2022-23. Wording is as printed in that syllabus. Module numbering is as printed there too.
The complete syllabus
This subject is cut from the University circular for its year. Open a document here if you want the whole thing rather than a single subject.