Studying at the University of Verona
Here you can find information on the organisational aspects of the Programme, lecture timetables, learning activities and useful contact details for your time at the University, from enrolment to graduation.
Academic calendar
The academic calendar shows the deadlines and scheduled events that are relevant to students, teaching and technical-administrative staff of the University. Public holidays and University closures are also indicated. The academic year normally begins on 1 October each year and ends on 30 September of the following year.
Course calendar
The Academic Calendar sets out the degree programme lecture and exam timetables, as well as the relevant university closure dates..
| Period | From | To |
|---|---|---|
| Primo semestre | Oct 4, 2021 | Jan 28, 2022 |
| Secondo semestre | Mar 7, 2022 | Jun 10, 2022 |
| Session | From | To |
|---|---|---|
| Sessione invernale d'esame | Jan 31, 2022 | Mar 4, 2022 |
| Sessione estiva d'esame | Jun 13, 2022 | Jul 29, 2022 |
| Sessione autunnale d'esame | Sep 1, 2022 | Sep 29, 2022 |
| Session | From | To |
|---|---|---|
| Sessione Estiva | Jul 15, 2022 | Jul 15, 2022 |
| Sessione Autunnale | Oct 14, 2022 | Oct 14, 2022 |
| Sessione Invernale | Mar 14, 2023 | Mar 14, 2023 |
| Period | From | To |
|---|---|---|
| Festa di Tutti i Santi | Nov 1, 2021 | Nov 1, 2021 |
| Festa dell'Immacolata Concezione | Dec 8, 2021 | Dec 8, 2021 |
| Festività natalizie | Dec 24, 2021 | Jan 2, 2022 |
| Festa dell'Epifania | Jan 6, 2022 | Jan 7, 2022 |
| Festività pasquali | Apr 15, 2022 | Apr 19, 2022 |
| Festa della Liberazione | Apr 25, 2022 | Apr 25, 2022 |
| Festività Santo Patrono di Verona | May 21, 2022 | May 21, 2022 |
| Festa della Repubblica | Jun 2, 2022 | Jun 2, 2022 |
| Chiusura estiva | Aug 15, 2022 | Aug 20, 2022 |
Exam calendar
Exam dates and rounds are managed by the relevant Science and Engineering Teaching and Student Services Unit.
To view all the exam sessions available, please use the Exam dashboard on ESSE3.
If you forgot your login details or have problems logging in, please contact the relevant IT HelpDesk, or check the login details recovery web page.
Should you have any doubts or questions, please check the Enrolment FAQs
Academic staff
Study Plan
The Study Plan includes all modules, teaching and learning activities that each student will need to undertake during their time at the University. Please select your Study Plan based on your enrolment year.
| Modules | Credits | TAF | SSD |
|---|
| Modules | Credits | TAF | SSD |
|---|
1° Year
| Modules | Credits | TAF | SSD |
|---|
2° Year
| Modules | Credits | TAF | SSD |
|---|
| Modules | Credits | TAF | SSD |
|---|
Legend | Type of training activity (TTA)
TAF (Type of Educational Activity) All courses and activities are classified into different types of educational activities, indicated by a letter.
Deep Learning (2021/2022)
Teaching code
4S009018
Credits
6
Language
English
Scientific Disciplinary Sector (SSD)
INF/01 - INFORMATICS
The teaching is organized as follows:
Teoria
Laboratorio
Learning outcomes
The course provides the theoretical foundations and describes advanced methodologies related to the area of deep learning. Deep learning solves machine learning and pattern recognition problems through the neural network paradigm and the numerical optimization. The course is also highly implementative, offering specific programming concepts for professional Python-based systems. Deep learning aims to build mainly nonlinear regression and classification systems based on neural networks. A neural network can be seen as a simple computational structure (multinomial logistic functions + non-linearities, intertwined together) which is enhanced by structuring itself at various levels (layers) of various types (fully connected, convolutional, recurring, and many others). Each of these structures underlies a very precise theory (for example the dropout of neural networks refers to the Bayesian approximation) which will be formally detailed by the teacher. In this way, the student will not only be a user of the discipline, but will manage it by acquiring formal critical skills. Particular attention will also be paid to the aspect of explainability, that is, all those techniques capable of communicating critical cases in which a particular neural network is unable to solve problems. The course will provide case studies on which to apply the studied techniques, to make them immediately usable in a professional context.
Program
The course presents a series of state-of-the-art topics in the field of recognition. Deep learning will be analyzed starting from its methodological basis. Each topic will be explained through updated articles together with the lesson slides. The following books are suggested as a reference:
- Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag New York, Inc., Secaucus, NJ, USA.
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep learning. MIT Press, 2016.
Topics:
- Linear Regression, ridge, LASSO, elastic net
- Multinomial Logistic Classifier,
- Neural Networks,
- Backpropagation,
- Convolutional Neural Network,
- Recurrent Neural Networks
- Long Short-Term Memory machine
- Transformer Network
Examination Methods
The exam involves the discussion of a code project, which proposes a solution to an industrial classification problem. The final score will depend on the classification figure of merits achieved by the classifier and the theoretical motivations that prompted the student to choose a particular algorithm.
Type D and Type F activities
Le attività formative di tipologia D sono a scelta dello studente, quelle di tipologia F sono ulteriori conoscenze utili all’inserimento nel mondo del lavoro (tirocini, competenze trasversali, project works, ecc.). In base al Regolamento Didattico del Corso, alcune attività possono essere scelte e inserite autonomamente a libretto, altre devono essere approvate da apposita commissione per verificarne la coerenza con il piano di studio. Le attività formative di tipologia D o F possono essere ricoperte dalle seguenti attività.
1. Insegnamenti impartiti presso l'Università di Verona
Comprendono gli insegnamenti sotto riportati e/o nel Catalogo degli insegnamenti (che può essere filtrato anche per lingua di erogazione tramite la Ricerca avanzata).
Modalità di inserimento a libretto: se l'insegnamento è compreso tra quelli sottoelencati, lo studente può inserirlo autonomamente durante il periodo in cui il piano di studi è aperto; in caso contrario, lo studente deve fare richiesta alla Segreteria, inviando a carriere.scienze@ateneo.univr.it il modulo nel periodo indicato.
2. Attestato o equipollenza linguistica CLA
Oltre a quelle richieste dal piano di studi, per gli immatricolati dall'A.A. 2021/2022 vengono riconosciute:
- Lingua inglese: vengono riconosciuti 3 CFU per ogni livello di competenza superiore a quello richiesto dal corso di studio (se non già riconosciuto nel ciclo di studi precedente).
- Altre lingue e italiano per stranieri: vengono riconosciuti 3 CFU per ogni livello di competenza a partire da A2 (se non già riconosciuto nel ciclo di studi precedente).
Tali cfu saranno riconosciuti, fino ad un massimo di 6 cfu complessivi, di tipologia F se il piano didattico lo consente, oppure di tipologia D. Ulteriori crediti a scelta per conoscenze linguistiche potranno essere riconosciuti solo se coerenti con il progetto formativo dello studente e se adeguatamente motivati.
Gli immatricolati fino all'A.A. 2020/2021 devono consultare le informazioni che si trovano qui.
Modalità di inserimento a libretto: richiedere l’attestato o l'equipollenza al CLA e inviarlo alla Segreteria Studenti - Carriere per l’inserimento dell’esame in carriera, tramite mail: carriere.scienze@ateneo.univr.it
3. Competenze trasversali
Scopri i percorsi formativi promossi dal TALC - Teaching and learning center dell'Ateneo, destinati agli studenti regolarmente iscritti all'anno accademico di erogazione del corso https://talc.univr.it/it/competenze-trasversali
Modalità di inserimento a libretto: non è previsto l'inserimento dell'insegnamento nel piano di studi. Solo in seguito all'ottenimento dell'Open Badge verranno automaticamente convalidati i CFU a libretto. La registrazione dei CFU in carriera non è istantanea, ma ci saranno da attendere dei tempi tecnici.
4. Periodo di stage/tirocinio
Oltre ai CFU previsti dal piano di studi (verificare attentamente quanto indicato sul Regolamento Didattico): qui informazioni su come attivare lo stage.
Insegnamenti e altre attività che si possono inserire autonomamente a libretto
| years | Modules | TAF | Teacher |
|---|---|---|---|
| 1° 2° | Data Analysis for Biomedical Sciences | D |
Gloria Menegaz
(Coordinatore)
|
| 1° 2° | Introduction to Robotics to students of scientific courses. | D |
Paolo Fiorini
(Coordinatore)
|
| 1° 2° | Matlab-Simulink programming | D |
Bogdan Mihai Maris
(Coordinatore)
|
| years | Modules | TAF | Teacher |
|---|---|---|---|
| 1° 2° | Introduction to Robotics to students of scientific courses. | D |
Paolo Fiorini
(Coordinatore)
|
| 1° 2° | Introduction to 3D printing | D |
Franco Fummi
(Coordinatore)
|
| 1° 2° | HW components design on FPGA | D |
Franco Fummi
(Coordinatore)
|
| 1° 2° | Rapid prototyping on Arduino | D |
Franco Fummi
(Coordinatore)
|
| 1° 2° | Protection of intangible assets (SW and invention)between industrial law and copyright | D |
Roberto Giacobazzi
(Coordinatore)
|
| years | Modules | TAF | Teacher |
|---|---|---|---|
| 1° 2° | Python programming language | D |
Giulio Mazzi
(Coordinatore)
|
Career prospects
Module/Programme news
News for students
There you will find information, resources and services useful during your time at the University (Student’s exam record, your study plan on ESSE3, Distance Learning courses, university email account, office forms, administrative procedures, etc.). You can log into MyUnivr with your GIA login details.
Further services
I servizi e le attività di orientamento sono pensati per fornire alle future matricole gli strumenti e le informazioni che consentano loro di compiere una scelta consapevole del corso di studi universitario.
Graduation
List of theses and work experience proposals
| theses proposals | Research area |
|---|---|
| Domain Adaptation | Computer Science and Informatics: Informatics and information systems, computer science, scientific computing, intelligent systems - Computer graphics, computer vision, multi media, computer games |
| Domain Adaptation | Computer Science and Informatics: Informatics and information systems, computer science, scientific computing, intelligent systems - Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video) |
| Domain Adaptation | Computing Methodologies - IMAGE PROCESSING AND COMPUTER VISION |
| Domain Adaptation | Computing methodologies - Machine learning |
Attendance
As stated in point 25 of the Teaching Regulations for the A.Y. 2021/2022, attendance at the course of study is not mandatory.Please refer to the Crisis Unit's latest updates for the mode of teaching.
