Prerequisite course: Probability, Data Structures and Algorithms

Learning Objectives

To know the role of probability theory in solving problems in the real world related to data. The problems can range from predicting future consequences to analysing historical data. The domain of problems can be healthcare, education, governance to mention a few.

Learning Outcomes

At the end of the course, the students should be able to precisely define, and solve classical and commonly encountered problems along with deriving connections across multiple similar solutions and models.

Course content

  1. Introduction: Probabilistic data analysis. [3]

  2. Bayesian models: classifications, clustering, regression. Sequential Bayesian learning for Big-Data. [18]

  3. Hierarchical Bayesian models: generative modeling. Topic models. Markov models. Inference, and estimation techniques for probabilistic models: MCMC, Gibbs sampling, variational inference. [18]

  4. Case study using Natural Language Processing/Computer Vision/Bioinformatics. [3]

Text books

  1. Pattern Recognition and Machine Learning. Christopher Bishop. Springer. 2006. ISBN-13 978-0-387-31073-2.

References

  1. Ian Goodfellow, YoshuaBengio and Aaron Courville. Deep Learning .TheMIT Press, 2016. ISBN13 :978-0262035613.
  2. Introduction to Probability Models, Eleventh Edition. Sheldon Ross. 11thEdition. Academic Press. 2014. ISBN-13: 978-0124079489.
  3. The Algorithmic Foundation of Differential Privacy. Cynthia Dwork. 2014. Foundations and Trends in Theoretical Computer Science. Now Publishers Inc. ISBN-13: 978-1601988188.
  4. Bayesian Data Analysis. Andrew Gelman, John Carlin, Hal Stern, David Dunson, Aki Vehtari, and Donald Rubin. Third Edition. 2013. ISBN-13:978-1439840955.

Past Offerings