Lab: Generative Artificial Intelligence Literacy
A.Y. 2025/2026
Learning objectives
Undefined
Expected learning outcomes
Undefined
Lesson period: Third trimester
Assessment methods: Giudizio di approvazione
Assessment result: superato/non superato
Single course
This course cannot be attended as a single course. Please check our list of single courses to find the ones available for enrolment.
Course syllabus and organization
Single session
Responsible
Lesson period
Third trimester
Course syllabus
The following is a TBC breakdown of the module, each unit consisting of 45/60 minutes of work.
Here 'l' stands for 'lecture' and 'p' stands for 'practicum' or 'lab.'
l.0
A brief introduction to AI
l.1
A stats refresher
p.0
Handling text with computers
l.2, l.3
A brief introduction to Natural Language Processing
p.1
Online LLM prompts
l.4
Attention
l.5
Diffusion
p.2
Enriching prompts
l.6
The text-to-image bridge
p.3
Embedding prompts
p.4
Evaluating responses
l.7
Data sources and ethical aspects
l.8
Comparing and evaluating generated text
p.5
Huggingface
p.6
Onboard GenAI solutions
p.7
GenAI on your laptop
l.9
Conclusions and exam project instructions
p.8, p.9
Work on personal project, with supervision.
Here 'l' stands for 'lecture' and 'p' stands for 'practicum' or 'lab.'
l.0
A brief introduction to AI
l.1
A stats refresher
p.0
Handling text with computers
l.2, l.3
A brief introduction to Natural Language Processing
p.1
Online LLM prompts
l.4
Attention
l.5
Diffusion
p.2
Enriching prompts
l.6
The text-to-image bridge
p.3
Embedding prompts
p.4
Evaluating responses
l.7
Data sources and ethical aspects
l.8
Comparing and evaluating generated text
p.5
Huggingface
p.6
Onboard GenAI solutions
p.7
GenAI on your laptop
l.9
Conclusions and exam project instructions
p.8, p.9
Work on personal project, with supervision.
Prerequisites for admission
Basic computer literacy as taught in most BA/BSc courses.
Familiarity with any Linux/MacOs/Win filesystem and with Spreadsheet operations is preferable.
The lab part might involve running simple Python scripts.
Familiarity with any Linux/MacOs/Win filesystem and with Spreadsheet operations is preferable.
The lab part might involve running simple Python scripts.
Teaching methods
About half of the class time will be allocated to frontal lectures explaining computer-based text handling and generation.
The other half will be hands-on accessing and experimenting Generative AI solutions.
We will move from online queries to HuggingFace to running private instances on one's laptop.
At the time of writing the choice engine for the latter is NVIDIA Memotron Nano.
The other half will be hands-on accessing and experimenting Generative AI solutions.
We will move from online queries to HuggingFace to running private instances on one's laptop.
At the time of writing the choice engine for the latter is NVIDIA Memotron Nano.
Teaching Resources
Contents, resources and study materials will be made available weekly from the class repository and linked from the relevant MyAriel page.
Materials seen in class are kept in a Github repository maintained by the instructor:
https://github.com/ale66/learn-genai
Background readings, in-class presentations, their order and the study materials are constantly reviewed, updated and amended to adjust to the pace of the class.
Materials seen in class are kept in a Github repository maintained by the instructor:
https://github.com/ale66/learn-genai
Background readings, in-class presentations, their order and the study materials are constantly reviewed, updated and amended to adjust to the pace of the class.
Assessment methods and Criteria
A take-home personal project that is related to the student's upcoming graduation project.
Professor(s)
Reception:
by email appointment
MS Teams platform