Data Science for Engineers

Course philosophy and introduction to R  

Linear algebra for data science 

1. Algebraic view - vectors, matrices, product of matrix & vector, rank, null space, solution of over-determined set of equations and pseudo-inverse) 

2. Geometric view - vectors, distance, projections, eigenvalue decomposition

Statistics (descriptive statistics, notion of probability, distributions, mean, variance, covariance, covariance matrix, understanding univariate and multivariate normal distributions, introduction to hypothesis testing, confidence interval for estimates)  

Optimization

1. Optimization

2. Typology of data science problems and a solution framework

1. Simple linear regression and verifying assumptions used in linear regression 

2. Multivariate linear regression, model assessment, assessing importance of different variables, subset selection

Classification using logistic regression

Classification using kNN and k-means clustering

Dr. Regaswamy is a Professor in the Dept. of Chemical Engineering, IIT Madras. Prior to this, he was a Professor of Chemical Engineering and Co-Director of the Process Control and Optimization Consortium at Texas Tech University, Lubbock, USA. He was also a professor and associate professor at Clarkson University, USA and an assistant professor at IIT Bombay. His major research interests are in the areas of fault detection and diagnosis and development of data science algorithms for manufacturing industries.

Prof.Shankar Narasimhan is currently a Professor in the department of Chemical Engineering at IIT Madras. His major research interests are in the areas of data mining, process design and optimization, fault detection and diagnosis and fault tolerant control. He has co-authored several important papers and a book titled Data Reconciliation and Gross Error Detection: An Intelligent Use of Process Data which has received critical appreciation in India and abroad.