Applied Machine Learning and Data Analytics

Applied Machine Learning and Data Analytics

 

  • Entry Pass

    Last Date: 29-07-2017

    INR 35000
  • Special Offer

    Sale Date Ended

    INR 25000
    Sold Out
  • Early Bird Offer

    Sale Date Ended

    INR 30000
    Sold Out

Invite friends

Contact Us

Page Views : 59

About The Event

Course Duration:              80 Hours

 

Course Evaluation:           Module wise quizzes and a projects

Course Objective:             This course aims to provide solid understanding of data science theory and applications in business. Focus will be on the underlying scientific concepts while also accounting for recent progress made by the scientific and technical community in the field of data science. The course will draw examples from various case studies and thus emphasis will be on application. Associate shall get a hands-on experience in the application of these techniques for addressing practical problems from retail domain. 

 

Instructor's Bio:  

 

The course will be conducted by an Assistant Professor at IIT Kharagpur. His teaching interests include non-linear programming, multivariate statistical models, generalized linear models, machine learning and data analytics. He has offered various courses, lectures and workshops on applied machine learning and data analytics at IIT Kharagpur and other premier institute.

 

 

 

 

Course Content

 

Module A: Basics (20 Hours)

 

A.1         Probability and Statistics basics

 

  1. Sample Space and Events
  2. Random variables
  3. Sampling and distributions
  4. Parameter Estimation
  5. Hypothesis Testing
  6. Multivariate Normal Distribution (Gaussian)
  7. ANOVA, ANCOVA, MANOVA, MANCOVA
  8. Non-parametric Tests

 

A.2         Matrix Algebra and Random Vectors basics

 

  1. Matrix and Vector Algebra
  2. Positive Definite Matrices
  3. Square Root Matrix
  4. Random Vectors and Matrices
  5. Matrix Inequalities and Maximization
  6. Eigen Values and Eigen vectors
  7. Spectral Decomposition
  8. Singular Value Decomposition (SVD)
  9. Non Negative Matrix Factorization (NMF)

 

A.3         Multivariable Calculus and optimization basics

 

  1. Multivariate Differential & Integral calculus
  2. Directional Derivatives
  3. Convex/Non-convex functions
  4. Fermat’s Theorem
  5. Lagrange function
  6. KKT conditions          
  7. Multivariable Search techniques

 

                                                     i.     Derivative-free: Dichotomous,  Fibonacci, Golden selection

 

                                                    ii.     Derivative based: Steepest Descent, Gradient descent, Newton’s method

 

                                                   iii.     Random Search: Genetic Algorithm

 

A.4         Python Programming basics

 

 

 

Module B: Learning Concepts (10 Hours)

 

  1. Supervised and Unsupervised Learning
  2. Bias/Variance tradeoff
  3. Model Selection
  4. Cross Validation
  5. VC Dimension
  6. Regularization theory

 

Module C: Statistical Learning Models (20 Hours)

 

  1. Multivariate Linear regression
  2. Principle and Factor Analysis
  3. Discrimination and Classification
  4. Multivariate normal
  5. Fishers linear discriminant
  6. Clustering
  7. Expectation Maximization
  8. K-means, Hierarchal and DBSCAN
  9. Generalized Linear Models (Exponential Family)
  10. Logistic and Multinomial regression
  11. Poisson regression and log-linear models
  12. Survival models

 

Module D: Machine Learning Models (30 Hours)

 

  1. Artificial Neural Network
  2. Deep Learning
  3. Support Vector Machines and Kernel Regression
  4. Hidden Markov Models
  5. Decision Trees
  6. Ensemble Methods
  7. Random Forest
  8. Boosting: Gradient/XG, Ada
  9. Bagging
  10. Regularization model
  11. Feature selection 

 

Course fees can also be paid by account transfer