Introduction to Machine Learning Course | IIT Madras Prof. Balaraman Ravindran
Course Details
| Exam Registration | 19902 |
|---|---|
| Course Status | Ongoing |
| Course Type | Elective |
| Language | English |
| Duration | 12 weeks |
| Categories | Computer Science and Engineering, Artificial Intelligence, Data Science, Programming, Robotics |
| Credit Points | 3 |
| Level | Undergraduate/Postgraduate |
| Start Date | 19 Jan 2026 |
| End Date | 10 Apr 2026 |
| Enrollment Ends | 02 Feb 2026 |
| Exam Registration Ends | 20 Feb 2026 |
| Exam Date | 17 Apr 2026 IST |
| NCrF Level | 4.5 — 8.0 |
Introduction to Machine Learning: A Foundational 12-Week Journey
In an era defined by data, Machine Learning (ML) has emerged as a transformative force across industries. From powering recommendation systems to enabling autonomous vehicles, the applications are vast and growing. If you're a student or professional looking to build a strong, mathematically-grounded foundation in this critical field, the Introduction to Machine Learning course offered by Indian Institute of Technology (IIT) Madras is an exceptional starting point.
This 12-week elective course, designed for senior undergraduate and postgraduate students, demystifies core ML concepts from a principled perspective. Led by an esteemed expert, the curriculum is structured to take you from fundamental theory to advanced algorithms, equipping you with the knowledge sought after in the data-driven industry.
Your Expert Instructor: Prof. Balaraman Ravindran
The course is led by Prof. Balaraman Ravindran, a Professor in Computer Science at IIT Madras and a Mindtree Faculty Fellow. With nearly two decades of dedicated research experience, primarily in machine learning and reinforcement learning, Prof. Ravindran brings immense depth to the subject. His current research focuses on learning from interactions, spanning data mining, social network analysis, and reinforcement learning. Learning from an instructor of this caliber ensures you gain insights rooted in cutting-edge academic research.
Who Is This Course For?
This course is meticulously designed for:
- Senior Undergraduate (UG) & Postgraduate (PG) Students (BE/ME/MS/PhD) in Computer Science, AI, Data Science, or related fields.
- Professionals aiming to transition into data science, analytics, or machine learning roles.
- Anyone with a technical background seeking a rigorous, theory-informed introduction to ML.
Prerequisites & Course Level
To make the most of this course, students should have:
- Programming knowledge for completing assignments.
- Introductory-level familiarity with Probability Theory and Linear Algebra is highly beneficial. The course thoughtfully includes a recap week (Week 0) to refresh these essential mathematical concepts, along with Convex Optimization.
Detailed 12-Week Course Layout
The curriculum is comprehensive, building concepts week-by-week:
| Week | Topics Covered |
|---|---|
| Week 0 | Probability Theory, Linear Algebra, Convex Optimization (Recap) |
| Week 1 | Introduction: Statistical Decision Theory, Regression, Classification, Bias-Variance Tradeoff |
| Week 2 | Linear & Multivariate Regression, Subset Selection, Shrinkage Methods, PCA Regression |
| Week 3 | Linear Classification, Logistic Regression, Linear Discriminant Analysis |
| Week 4 | Perceptron, Support Vector Machines (SVM) |
| Week 5 | Neural Networks: Perceptron Learning, Backpropagation, Training/Validation, MLE/MAP Estimation |
| Week 6 | Decision Trees & Regression Trees, Pruning, Evaluation Measures |
| Week 7 | Bootstrapping & Cross-Validation, ROC Curves, Ensemble Methods (Bagging, Stacking, Boosting) |
| Week 8 | Gradient Boosting, Random Forests, Naive Bayes, Bayesian Networks |
| Week 9 | Undirected Graphical Models, Hidden Markov Models (HMM), Belief Propagation |
| Week 10 | Clustering: Partitional, Hierarchical, Density-based (DBSCAN), BIRCH, CURE |
| Week 11 | Gaussian Mixture Models, Expectation-Maximization (EM) Algorithm |
| Week 12 | Learning Theory, Introduction to Reinforcement Learning (RL) |
Recommended Textbooks
The course aligns closely with seminal texts in the field, providing excellent resources for deeper study:
- Primary: The Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani, and Jerome H. Friedman (freely available online).
- Optional: Pattern Recognition and Machine Learning by Christopher Bishop.
Industry Relevance & Support
The skills imparted in this course are in high demand. Any company operating in the data analytics, data science, artificial intelligence, or big data domain will value the comprehensive understanding this course provides. Completing it signals a strong foundational competence in machine learning principles and algorithms, making you a competitive candidate for roles in these fast-growing sectors.
Whether you aim to advance in academia or build a career in industry, this Introduction to Machine Learning course from IIT Madras offers the rigorous, structured learning path you need to succeed in the world of AI and data science.
Enroll Now →