Logistics

• Lectures (D Slot):
• 📅 Monday: 11:00 AM – 12:00 PM
• 📅 Tuesday: 10:00 AM – 11:00 AM
• 📅 Wednesday: 9:00 AM – 10:00 AM
• 📅 Thursday: 12:00 PM – 1:00 PM (Tutorials)


• Location: 📍 CRC 101


• Office hours:
• Balaji: Mon 12 - 1:00pm
• TA Office hours: TBD


• Grading Policy:
• 📖 Quiz 1 & Quiz 2: 25%
• 📝 End-Sem Exam: 50%
• 📚 Assignments: 25% (Not for submission)
  Assignments will be provided throughout the semester but are not required for submission. A selection of questions from the assignments will appear in Quiz 1, Quiz 2, and the End-Sem Exam, collectively contributing to a total weightage of 25%.
• Final Grade Cutoffs:
• S: ≥ 90
• A: ≥ 80
• B: ≥ 70
• C: ≥ 60
• D: ≥ 50
• E: ≥ 40
• While minor adjustments (typically by 1–2 points) to the above cutoffs may be made, given that the course has over 100 students, it is inevitable that some students may miss a grade boundary by < 1 mark. Unfortunately, this is an inherent aspect of the grading system, and no exceptions can be made in such cases.
• Students are strongly encouraged to focus on performing their best throughout the course and in the exams, rather than requesting leniency in grades after results are announced.


• Course Forum: We will be having a Discord channel for the course very soon. Students should ask all course-related questions on the channel. Course-related announcements will also be made on the Discord channel.


• Academic accommodations: If you need an academic accommodation based on a disability, you should initiate the request with the Academic Section in advance.


• Honor code: Very important. See Honor Code.

Overview

What is this course about?

Foundations of Machine Learning (DA5400) is an introductory course designed to provide a strong conceptual foundation in classical machine learning.

The course covers fundamental algorithms, including regression, classification, decision trees, ensemble methods, support vector machines, clustering, and dimensionality reduction, with a focus on their mathematical formulation and theoretical underpinnings.

Emphasis is placed on understanding core principles rather than implementation, making it ideal for students seeking a rigorous, algorithmic perspective on machine learning.

While deep learning is not a focus, the course equips students with the necessary background to pursue more advanced studies in areas such as deep learning, probabilistic modeling, and modern AI techniques.

Prerequisites

Students are expected to have the following background:

• Knowledge of basic programming, at a level sufficient to write a reasonably non-trivial computer program, ideally in Python.
• An undergraduate level understanding of Linear Algebra, Probability, and Multivariable Calculus.
• Lack of fear of Mathematics or Programming

Honor Code

Permissive but strict. If unsure, please ask!

• Attendance is mandatory. NOT OK to skip classes for non-medical reasons.
• OK to use Gen AI tools or the internet to solve Exercise problems given in the course.
• NOT OK to copy during the exams. This will lead to immediate referral to the Disciplinary committee and a U grade in the course.

Audit policy

Anyone who wishes to drop the course, but sit through the classes is welcome to.

The slides, codes, assignments, will be made publicly available on the Syllabus page. But this depends on the time I have to do so. Please always take notes in class and do not depend on me uploading them.

Reference Text

The course relies on lecture notes. Books will be shared as required.