MA2221 – Foundational Mathematics for Machine Learning
📢 Announcements New updates
- Lab 9: The lab on the Machine Learning Pipeline is now available in the
notebooks/notebook_ML_Pipeline.ipynbfile. You need to submit the completed notebook as lab assignment 3. - Lab 8: The lab on Probability is now available in the
notebooks/notebook_probability.ipynbfile. You need to submit the completed notebook as lab assignment 2. - Lab 7: The lab on Data Handling is now available in the
notebooks/notebook_DataHandling.ipynbfile. You need to submit the completed notebook as lab assignment 1.
ℹ️ Course Information
Instructor: Biswarup Biswas
Institution: Mahindra University
📅 Class Schedule
| Session Type | Day | Time | Venue |
|---|---|---|---|
| Practical | Monday | 15:35 – 17:30 | Computer Lab 3 |
| Lecture | Tuesday | 09:25 – 10:20 | ELT6 |
| Lecture | Wednesday | 10:35 – 11:30 | ELT6 |
| Lecture | Thursday | 14:35 – 15:30 | ELT6 |
🎯 About the Course
This course develops the rigorous mathematical foundations of Machine Learning, focusing on the four pillars: Linear Algebra, Analytic Geometry, Matrix Decompositions, and Continuous Optimization. We treat machine learning as the art of function approximation—transforming raw data into geometric representations and probabilistic models. By exploring the transition from theory to practice ("Model Meets Data"), students gain the language to handle high-dimensional spaces, quantify uncertainty, and optimize complex loss surfaces. The course empowers students to not only use ML tools but to understand the underlying principles of stability, convergence, and generalization.