ML-s2-2024
Machine Learning @Sapienza
Course material, 2nd semester a.y. 2023/2024, Mathematical Sciences for AI
News 🗞️
- 12/05/2024: Starting from May 13th, lectures will be held in Aula C instead of Aula Picone.
- 29/04/2024: The midterm sheet is published, scroll down to download it.
- 20/04/2024: Instructions for the final exam have been updated; scroll down to the Grading 📊 section for details.
- 17/04/2024: The midterm self-assessment will take place on April 29th.
- 26/03/2024: Fixed a mistake in the calculation of the gradient in notebook 03.
- 22/03/2024: Mark your calendars! The exam dates ✍ are now published (scroll down to the Grading section).
- 12/03/2024: Added an explanation for the solution to the final exercise of notebook 01.
- 10/03/2024: The lecture of Monday 11th March will be a lab session, and Tuesday 12th March will be theory!
- 06/02/2024: The course website is online. Welcome to ML 2023/24! The course will start on Mon 4th March.
Logistics 🧭
Lecturer: Prof. Emanuele Rodolà
Assistants: Dr. Adrian Minut and Dr. Daniele Solombrino
When: Mondays 10:00–13:00 and Tuesdays 8:00–11:00
Where:
Until May 6th: Aula Picone - Piano Terra, Dip. di Matematica Castelnuovo (CU006-E01PTEL008)
From May 13th: Aula C - Piano Terra, Dip. di Matematica Castelnuovo (CU006-E01PTEL008)
There is no virtual classroom, and the lectures will not be recorded.
Pre-requisites 🔑
Python fundamentals; calculus; linear algebra.
Textbook and reading material 📖
Due to the continuously evolving nature of the topic, there is no fixed textbook as a reference. Specific material in the form of scientific articles and book chapters will be given throughout the lectures.
Grading 📊
Exam dates
- 24 June 2024
- 15 July 2024
- 17 September 2024
- 24 January 2025
Evaluation proceeds according to the following steps:
- A final written exam (mandatory, accounts for 30% of the final grade)
- A project (mandatory, accounts for 70% of the final grade)
Example 1: Project: 30; Written exam: 20; Final grade: 27. Example 2: Project: 26; Written exam: 30; Final grade: 27.
There will also be a midterm self-evaluation test; it is optional, and does not concur to the final grade.
We may require an oral exam in doubtful cases or whenever necessary.
Lectures 🗣️
| Date | Topic | Reading | Code & Data |
|---|---|---|---|
| Mon 4 Mar | 🌐 Introduction; Talking sense about data I | slides | |
| Tue 5 Mar | 🔢 Talking sense about data II; Linear algebra revisited; Introduction to Python notebooks and NumPy | slides ; linear algebra recap ; matrix notes | |
| Mon 11 Mar | 🀠 Array manipulation |  |
|
| Tue 12 Mar | 📏 Regression problems | slides ; matrix gradient notes | |
| Mon 18 Mar | 📏 Linear regression and scikit-learn | 🐱 |
|
| Tue 19 Mar | 📉 Regularization; Stochastic gradient descent | slides 1 ; slides 2 | |
| Mon 25 Mar | 📉 Stochastic gradient descent | |
|
| Tue 26 Mar | 🔁 Multi-layer perceptron and back-propagation | slides | |
| Mon 01 Apr | 🐇 Easter holidays | ||
| Tue 02 Apr | 🐇 Easter holidays | ||
| Mon 08 Apr | 🔥 PyTorch and Deep Learning I | |
|
| Tue 09 Apr | 🔥 PyTorch and Deep Learning II | use yesterday’s notebook | |
| Mon 15 Apr | 👻 PCA, spectra, and low-rank approximations | slides | |
| Tue 16 Apr | 👻 Principal Component Analysis | 🦒 😀 |
|
| Mon 22 Apr | 🗺️ Manifold learning and dimensionality reduction | slides | |
| Tue 23 Apr | 🗺️ MDS and t-SNE | |
|
| Mon 29 Apr | 📝 Midterm | sheet | |
| Tue 30 Apr | Reinforcement Learning tutorial | slides | |
| Mon 06 May | 🔄 Midterm answers and Theory recap | ||
| Mon 13 May | 🔄 Notebook recap | ||
| Tue 14 May | 🗣️ Seminars | A bitter lesson ; Relative representations | |
| Mon 20 May | 🌳 Ensemble methods | upcoming | upcoming |
| Tue 21 May | TBD | ||
| Mon 27 May | TBD | ||
| Tue 28 May | TBD |
End