EEC 351: Fundamentals of AI/ML

Autumn 2026-27 · Department of Electrical Engineering, IIT Roorkee

Previous offering · Autumn 2025-26

Course information

SemesterAutumn 2026–27 InstructorParikshit Pareek · pareek [at] ee.iitr.ac.in LecturesThu · 16:05 – 17:00 @ GB005 · Fri · 17:05 – 18:00 @ GB005 Office hoursMon · 16:05 – 17:00 @ 214A, EE (instructor's office) PiazzaJoin the class · access code eec351 Teaching assistantsAyushi Jolotia · ayushi_j [at] ee.iitr.ac.in
Kaustubh Sharma · kaustubh_s [at] ee.iitr.ac.in

Announcements

  • 2026‑08‑25 — Extra Class PR1 · Probability Review on Monday, 31 August 2026, 16:05 – 17:00 @ GB005. Covers the Probability Review module (row PR1 under Course content); read the notes beforehand.
  • 2026‑08‑14 — The Linear Algebra Review module is live under Course content (rows LA1–LA8), with readings and interactive demos. You can browse all of our demos via explainer hub.
  • 2026‑08‑14 — Lecture schedule updated; see Course information above.
  • 2026‑07‑08 — First class is on Thursday, 16 July 2026.
  • 2026‑06‑18 — Course website for the Autumn 2026-27 offering is live. Announcements are posted here regularly; email is sent only when something is urgent.

Course objectives

  • Comprehend the historical evolution and foundational concepts of AI/ML.
  • Build mathematical intuition for machine-learning principles.
  • Explore core theoretical frameworks and evaluation strategies.

Course content

# Topic Slides Essential reading Additional Homework
0 Kick-off Slides -- The Course in One Picture --
1 History of AI and Machine Learning Slides Kolter & Do, Linear Algebra Review & Reference (CS229) §1–2
Boyd & Vandenberghe, Introduction to Applied Linear Algebra (VMLS) Ch. 1–3 		Watch Imitation Game
Turing Machine-- Short 		--
LA1 Notation & basic objects; vector/matrix products; properties of matrix multiplication -- Kolter & Do §1–2 3Blue1Brown, Essence of Linear Algebra
Deisenroth, Faisal & Ong, Mathematics for Machine Learning (Ch. 2–4) 		--
LA2 Transpose, symmetric matrices, trace; norms, Cauchy–Schwarz & cosine similarity -- Kolter & Do §3.2–3.5 EEC_351_Demo: ℓₚ Unit Balls
EEC_351_Demo: Cosine Similarity 		--
LA3 Matrix inverse; span, range & linear independence -- Kolter & Do §3.6–3.9 -- --
LA4 Linear projection & least squares -- Kolter & Do §3.9, §4.4 EEC_351_Demo: Least Squares Line Fitting --
LA5 Determinant; condition number & numerical sensitivity -- Kolter & Do §3.10 (condition number: supplementary — see Trefethen & Bau, Numerical Linear Algebra) -- --
LA6 Quadratic forms; symmetric & positive (semi)definite matrices -- Kolter & Do §3.11 -- --
LA7 Eigenvalues & eigenvectors; Diagonalization & the spectral theorem; eigenvalues as optimization -- Kolter & Do §3.12–3.13, §4.6 EEC_351_Demo: Eigenvectors as Fixed Directions
EEC_351_Demo: Rotate · Scale · Rotate
Setosa, Eigenvectors & Eigenvalues, Explained Visually 		--
LA8 SVD; PCA; Matrix calculus (Self) -- Kolter & Do §4.1–4.3 EEC_351_Demo: PCA Playground
Setosa, Principal Component Analysis, Explained Visually
Petersen & Pedersen, The Matrix Cookbook 		--
PR1 Probability Review (Self+Extra Class) -- Probability Review --

Assignments

  • Assignments will be posted here as they are released. TBA.
  • Python is the default programming language for the course; use it unless a task explicitly allows otherwise.
  • Submit via Moodle, Google Form, or GitHub — as specified in each assignment.
  • Honor code: any copying earns a zero on the assignment; more severe penalties may follow.
  • Late submissions incur penalties as announced with each assignment.

References & resources

Recommended texts

  • Probabilistic Machine Learning: An Introduction — Kevin Murphy, MIT Press, 2022/2023.
  • Learning from Data: A Short Course — Yaser S. Abu-Mostafa, Malik Magdon-Ismail & Hsuan-Tien Lin, AMLBook, 2017.

Supplementary

  • Coursera ML (Andrew Ng)
  • Relevant paper links shared on Piazza

Grading policy

  • CWS — 30 marks: announced & surprise quizzes; assignments & peer discussions.
  • MTE — 30 marks: written exam (any format).
  • ETE — 40 marks: written exam (any format).

Exam papers