Details of MA5214 (Spring 2020)

Level: 5 Type: Theory Credits: 4.0

Course CodeCourse NameInstructor(s)
MA5214 Machine Learning and Network Analysis Anirban Banerjee,
Koel Das

Syllabus
Machine Learning: Introduction to machine learning, overview of machine learning and basic concepts, feature selection and extraction, dimensionality reduction, small sample size problem, discriminant analysis, nearest neighbour, linear and quadratic classifiers, naive Bayes classifiers, support vector machine, clustering, EM algorithm, validation and bootstrapping, cross validation, bias-variance trade off.

Network Analysis: Networks and their representation weighted-unweighted and directed undirected networks, hypergraphs; Network structure degree, path, components; Measures degree centrality, closeness centrality, betweenness centrality, clustering coefficient, transitivity; Large-scale structure components, shortest path and small-world property, degree distributions, power law degree distribution, assortative mixing and modularity, network motifs; Network models random graph, small-world network, scale-free network, duplication and divergence model; Epidemics on networks SI model, SIR model, SIS model.

Prerequisite
Introduction to Graph Theory (MA3103), Numerical Analysis (MA3105) and Statistics-I (MA3205).

References
Suggested Texts:
1. Bishop, C.M., Pattern Recognition and Machine Learning, Springer.
2. Duda, R.O., Hart P.E. and Stork D.G., Pattern Classification, Wiley-Interscience.
2nd Edition.
3. Fukunaga K., Introduction to Statistical Pattern Recognition, Academic Press.
4. Newman, M.J., Networks: An Introduction, Oxford University Press.

Course Credit Options

Sl. No.ProgrammeSemester NoCourse Choice
1 IP 2 Not Allowed
2 IP 4 Not Allowed
3 IP 6 Not Allowed
4 MR 2 Not Allowed
5 MR 4 Not Allowed
6 MS 10 Elective
7 RS 1 Not Allowed
8 RS 2 Not Allowed