DLAI-s2-2022
Deep Learning & Applied AI @Sapienza
Course material, 2nd semester a.y. 2021/2022, Dept. of Computer Science
News
- 16/09/2022: The grades for the written exam of September 14th are available here
- 30/08/2022: The written exam of 14/09/2022 will be held in presence at 15:00, in Aula Alfa (via Salaria 113, ground floor).
- 11/07/2022: The grades for the written exam of July 08th are available here
- 13/06/2022: The grades for the written exam of June 10th are available here
- 05/05/2022: Today’s lecture will be streamed in the following Zoom meeting 909 702 0027, passcode: 887440
- 03/05/2022: The midterm grades are now published.
- 26/04/2022: The lectures of the 27th and 28th will regard an invited lecture and the midterm respectively, both during the standard lecture hours. The invited lecture will be given in the usual hybrid setting, so you can either come in presence or follow it remotely; the midterm will instead be performed remotely. The following Zoom meeting will be used for both lectures: Meeting ID: 889 5007 5810 Passcode: 774414.
- 21/04/2022: The list of projects is now published, please scroll down for more details.
- 13/04/2022: Please fill out the OPIS questionnaire (instructions here). The code for this course is X6SYL1ZK.
- 13/04/2022: The lecture of April 14th is cancelled due to Easter holidays, as per the academic calendar.
- 05/02/2022: The course website is online. Welcome to DLAI 2021/22!
Logistics
Lecturer: Prof. Emanuele Rodolà
Assistants: Dr. Luca Moschella, Dr. Donato Crisostomi
When: Wednesdays 16:00–19:00 and Thursdays 10:00–12:00 (official schedule)
Where:
Physical classrooms (capacity: 100%): Aula 2 (Wednesdays) and Aula 1 (Thursdays) - Aule L Via del Castro Laurenziano 7a
Virtual classroom: Zoom, Meeting ID: 475 234 9941, Passcode: 3K7xrM.
The lectures will not be recorded.
Q & A: Please use the Discussions system of Github. Here is the link to the course repository.
Pre-requisites
Programming fundamentals in Python; 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.
In addition, you can find here some supplementary course notes.
Grading
Evaluation proceeds according to the following steps:
- A midterm self-evaluation test (optional, does not concur to the final grade)
- A final written exam (mandatory, accounts for 60% of the final grade)
- A project (mandatory, accounts for 40% of the final grade)
- An oral exam (optional, attributes at most 3 points, added to or subtracted from the final grade)
The cum laude can be obtained only by taking the oral exam. For students who already have a very high score with written exam + project, the oral exam is meant to confirm the high score.
The list of projects is now published; please connect to the discord server to download the list. Each project must be accompanied with code + a 2 page report using a fixed template, also shared on the discord server. Projects can be made in groups of at most 2 students, but in this case, you must motivate this decision and get our approval beforehand.
Here you can find some example sheets of past written exams:
Lectures
| Date | Topic | Reading | Code & Data |
|---|---|---|---|
| Wed 23 Feb | Introduction | slides | |
| Thu 24 Feb | Data, features, and embeddings | slides | |
| Wed 02 Mar | Tensor manipulation |  |
|
| Thu 03 Mar | Linear algebra revisited | slides; notes on matrix meta-mechanics | |
| Wed 09 Mar | Tensor operations | |
|
| Thu 10 Mar | Linear regression, convexity, and gradients | slides | |
| Wed 16 Mar | Linear models and Pytorch Datasets | |
|
| Thu 17 Mar | Overfitting and going nonlinear | slides | |
| Wed 23 Mar | Logistic Regression and Optimization | |
|
| Thu 24 Mar | Stochastic gradient descent | slides | |
| Wed 30 Mar | Autograd and Modules | |
|
| Thu 31 Mar | Multi-layer perceptron and back-propagation | slides | |
| Wed 06 Apr | Convolutional Neural Networks | |
|
| Thu 07 Apr | Convolutional Neural Networks | slides | |
| Wed 13 Apr | Regularization, batchnorm and dropout | slides | |
| Wed 20 Apr | Uncertainty, regularization and the deep learning toolset | slides | |
| Thu 21 Apr | Deep generative models | slides | |
| Wed 27 Apr | Invited lecture: Antonio Norelli: “Towards an artificial scientist” | slides | |
| Thu 28 Apr | Midterm self-evaluation | sheet; grades | |
| Wed 04 May | Variational AutoEncoders | |
|
| Thu 05 May | Geometric deep learning | slides; video | |
| Wed 11 May | Self-attention and transformers | slides | |
| Thu 12 May | Adversarial training | slides | |
| Wed 18 May | CycleGAN and Adversarial Attacks | |
End