Page 186 - Microsoft Word - B.Tech. Course Structure (R20) WITH 163 CREDITS

on sparse cuts, dense submatrics and communities, community finding and graph partitioning, spectral
clustering applied to social networks
Random graphs: the G(n,p) Model, phase transitions, Giant component, cycle and full connectivity,
phase transitions for increasing properties branching process, CNF-SAT, non uniform models for
Random Graphs, growth models, small world graphs.
UNIT - V
Topic models: An idealized model, Nonnegative matrix factorization, NMF with Anchor terms, Hard
and soft clustering, the latent Dirichlet Allocation model for topics, the Dominant Admixture model,
formal assumptions, finding the term topic matrix, hidden markov models, graphical models and belief
propagation, Bayesian or belief networks, markov random fields, factor graphs, Tree algorithms,
message passing in general graphics, warning propagation, correlation between variables.
Textbooks:
1 .Fundamentals of data science by Arvim Blum, john hope croft, Ravindran Kannan
Reference Books:
1. High-Dimensional Probability: An Introduction with Applications in Data Science: 47
(Cambridge Series in Statistical and Probabilistic Mathematics, Series Number 47) by Roman
Vershynin Hardcover.

2. Understanding Machine Learning: From Theory to Algorithms by shaiselvshawrtaz, shai ben
David

Mdv
Mdv