Executive Certification in Advanced Data Science & Applications

• Overview of Course
• Introduction to Data Science
  • • Definition
    • Application areas
    •  Past, Present and Future
• The role of computation in Data science
• The role of mathematics in Data science

• Python
  
  • • Install and run Python, use IDE
    • Basic control structures
    • Importing and Manipulating data, tools for plotting
• R
  
  • • Getting started with R
    • Basics, control structures
    • Functions
    • Importing and manipulating data
• SQL
  
  • • Getting started with MySQL
    • Creating, inserting, retrieving records
    • Searching
    • Interfacing with Python and R

• Probability and Statistics

• • • Probability and counting, Bayes Theorem
    • Independence, Conditional Probability, Marginal Probability
    • Random Variables, Probability Distributions
    • Expectation, Variance, Covariance
    • Descriptive Statistics
    • Statistical Estimation
    • Hypothesis Testing
    • Predictive and Prescriptive Analytics
    • Practical Considerations in Data Science

• Linear Algebra

• • • Vectors and their operations
    • Matrices and their operations
    • Inner Products and norms
    • Matrix Decomposition – Eigenvalues, SVD
    • Applications

• Calculus and Optimisation

• • Partial Derivatives, Multivariable Calculus
  • Gradient, Jacobian
  • Automatic Differentiation
  • Constrained and Unconstrained Optimization
  • Gradient Descent and its variants

• Introduction to Machine Learning (3 hours) - From Data Science to Machine Learning, Learning paradigm, Components of a machine learning algorithm, Bias-Variance tradeoff, Model selection, Hyperparameters, Regularisation
• Supervised Learning (15 Hours)- Definition of supervised learning, data requirements, types of supervised learning problems, algorithms for regression and classification using supervised learning
  
  • • Linear Regression
    • Logistic Regression
    • Multiclass Classification
    • KNN
    • Decision tree
    • Random Forest
    • Support Vector Machines
    • Naïve Bayes
• Unsupervised Learning (7 Hours)- Definition of unsupervised learning, scenarios for unsupervised learning, types of data, examples, algorithms for unsupervised learning
  
  • • Agglomerative clustering
    • K-Means
    • Gaussian Mixture Models
    • Introduction to Generative Models
• Deep Learning (35 Hours)- Artificial Neural networks and its evolution, Backpropagation algorithm, modern applications including text & speech analysis, computer vision and natural language processing using deep learning. State of the art Deep Learning techniques in –
  
  • • Deep Neural Networks (DNN)
    • Convolutional Neural Networks (CNN)
    • Recurrent Neural Networks (RNN)
    • Transformers
    • Generative Adversarial Networks (GANs)

The techniques discussed in the previous 4 modules will be applied to problems in various domains here. The students can visit the campus to learn in person from domain experts. 
Practical applications will be selected from:

• Business Intelligence
• Business Analytics
• Sectorial Analytics (Marketing/ Finance/ Operations/ Supply Chain/ HRM)
• Computer Vision
• Language Modelling
• Applications in Engineering
• Healthcare
• Decision Making
• Project (In candidate's own time - 30 hours)