Course material, 2nd semester a.y. 2023/2024, Dept. of Computer Science

• 21/05/2024: The course if finished, see you at the exam!
• 15/05/2024: The project list is published here.
• 06/05/2024: The midterm results are published here.
• 05/05/2024: Due to the Professor and the entire research team attending ICLR 2024 to present several works, the lab session of Tue 07 May will be conducted offline. Reach out to the Professor via email for questions and issues on the notebook.
• 29/04/2024: The midterm sheet is published, scroll down to download it. If you want me to grade your answers, please send your solutions via email by 17:00.
• 16/04/2024: The midterm self-assessment will take place on April 29th.
• 22/03/2024: Mark your calendars! The exam dates ✍ are now published (scroll down to the Grading section).
• 20/03/2024: The lecture of Monday 8 April will be held in Aula RE3, Building A of Viale Regina Elena 291.
• 12/03/2024: Added an explanation for the solution of the final Exercise 3 of Notebook 2 (Tensor operations).
• 05/02/2024: The course website is online. Welcome to DLAI 2023/24! The course will start on Mon 26th February.

Lecturer: Prof. Emanuele Rodolà

Assistants: Dr. Donato Crisostomi, Dr. Adrian Minut, Dr. Daniele Solombrino

When: Mondays 14:00--16:00 and Tuesdays 13:00--16:00

Where:

Physical classroom: Aula L2 - Castro Laurenziano (RM018-E01PTEL026)

There is no virtual classroom, and the lectures will not be recorded.

Q & A: We will use a Discord server. More details during the first lessons.

Python fundamentals; calculus; linear algebra.

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, here you can find some supplementary course notes.

Accessibility 👁️‍🗨️: Starting from this semester, in an effort to create a more inclusive and accessible learning environment, all slides have been re-designed with readability in mind to support students with specific learning disabilities. We aim to ensure that everyone, regardless of learning differences, has equal access to the educational content provided. Should you need additional accommodations or have suggestions for further improving accessibility, please feel free to reach out.

Exam dates

• 5 June 2024
• 10 July 2024
• 10 September 2024

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)

We may require an oral exam in doubtful cases or whenever necessary.

• The project list for 2023/2024 is here.
• The template for the final project report is here.

Here you can find some example sheets of past written exams:

• June 2021
• July 2021
• September 2021
• October 2021
• January 2022
• February 2022

Date	Topic	Reading	Code & Data
Mon 26 Feb	Introduction	slides
Tue 27 Feb	Data, features, and embeddings	slides ; linear algebra recap ; matrix notes
Mon 04 Mar	Linear regression, convexity, and gradients	slides
Tue 05 Mar	Tensor basics and Tensor operations
Mon 11 Mar	Overfitting and going nonlinear	slides
Tue 12 Mar	Linear models and Pytorch Datasets
Mon 18 Mar	Stochastic gradient descent	slides
Tue 19 Mar	Logistic Regression and Optimization
Mon 25 Mar	Multi-layer perceptron and back-propagation	slides
Tue 26 Mar	Autograd and Modules
Mon 01 Apr	Easter holidays
Tue 02 Apr	Easter holidays
Mon 08 Apr	Convolutional neural networks	slides
Tue 09 Apr	Convolutional neural networks
Mon 15 Apr	Regularization, batchnorm and dropout	slides
Tue 16 Apr	Uncertainty, regularization and the deep learning toolset
Mon 22 Apr	PCA and VAEs	slides
Tue 23 Apr	Variational Autoencoders
Mon 29 Apr	Midterm	sheet
Tue 30 Apr	Lab catch-up		complete all the published notebooks
Mon 06 May	Adversarial learning	slides ; video
Tue 07 May	CycleGAN and Adversarial Attacks
Mon 13 May	Geometric deep learning	slides ; video
Tue 14 May	Reinforcement Learning tutorial	slides
Mon 20 May	Self-attention and transformers	slides ; Training neural networks effectively
Tue 21 May	Create your own agent 👤		source code

End