The Data Science Course

Machine learning (ML)

Objectives: Machine learning (ML) is the main workhorse of modern intelligent systems and Data analytics. In this course, we offer a hands on experience on different ML algorithms using Python, a programming language mainly intended for ML algorithms, without going into deeper mathematical details with the help of case studies and real world data. Learning Outcomes:

  • Basic to intermediate level of Python programming for data analysis including many analysis, visualization and scientific packages such as numpy, matplotlib, scipy, scikit-learn and panda.
  • Basic Machine learning algorithms starting from Linear Regression to Decision Trees [ SVM as an optional] and PCA / ICA / Clustering techniques.
  • You will be able to find variable selection, make intelligent decision based upon the data, classify important factors from less significant factors to make informed decision, predict future market prices such as stock market, analyze death risks of heart patients, make a marketing plan for a company.

Intended Audience

All graduates or final year students of Engineering and Computer sciences who are interested in pursuing Machine learning / intelligent programing / Artificial Intelligence / Data Science as a career. Professionals in different fields of technology are equally eligible to enhance their professional skill in AI.

Career Prospects: Machine learning programmer, Data Science engineer, Predictive analytics, Big data analyst

Course Contents

  • Basic Python programming
  • Variables and its types
  • Special structures (lists and tuples)
  • Conditional statements (if and if-else)
  • Loops (for and while)
  • Dictionaries and Tables
  • Function declaration
  • Class declaration and OOP in Python
  • Linear Regression (Prediction)
  • Linear Regression and its extensions
  • Model evaluation metrics
  • Lab 1: Plan a company’s advertisement campaign
  • Logistic Regression (Classification)
  • Binary Classification and decision boundaries
  • Lab2: Finding heart disease high risk patients
  • Naïve Bayes Classifier
  • Bayes theorem and its modifications
  • Lab3: Weather forecasting
  • K Nearest Neighbor
  • K value and its dependence on and
  • Lab 4: Stock market Prices Prediction
  • Regularized Prediction and Classification
  • norms penalty
  • Comparison of and  norm penalties
  • Lab 5: Who will be the winner in this cricket match?
  • Decision Trees
  • Bagging and Boosting
  • Random Forests
  • Lab 6: Detecting specific activity in Social Media
  • Dimensionality Reduction
  • Principal Component Analysis
  • Lab 7: Digit Recognition