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.
Type D and Type F activities
The educational activities of type D are chosen by the student, those of type F are further knowledge useful for entering the world of work (internships, soft skills, project works, etc.). According to the Didactic Regulations of the Course, some activities can be chosen and included autonomously in the booklet, others must be approved by a special committee to verify their consistency with the study plan. Type D or F educational activities can be covered by the following activities.
1. Teachings taught at the University of Verona.
Include the teachings listed below and/or in the Course Catalogue (which can also be filtered by language of delivery via Advanced Search).
Booklet entry mode: if the teaching is included among those listed below, the student can include it autonomously during the period in which the study plan is open; otherwise, the student must submit a request to the Secretariat, sending the form to carriere.scienze@ateneo.univr.it during the period indicated.
2. CLA certificate or language equivalency.
In addition to those required by the curriculum, the following are recognized for those matriculated from A.Y. 2021/2022:
- English language: 3 CFUs are recognized for each level of proficiency above the one required by the course of study (if not already recognized in the previous course of study).
- Other languages and Italian for foreigners: 3 cfu are recognized for each proficiency level starting from A2 (if not already recognized in the previous study cycle).
These cfu will be recognized, up to a maximum of 6 cfu in total, as type F if the teaching plan allows, or as type D. Additional elective credits for language knowledge may be recognized only if consistent with the student's educational project and if adequately justified.
Those enrolled until A.Y. 2020/2021 should consult the information found here.
Booklet entry mode: request the certificate or equivalency to the CLA and send it to the Student Secretariat - Careers for career entry of the exam, via email: carriere.scienze@ateneo.univr.it
3. Soft skills
Discover the training paths promoted by the University's TALC - Teaching and learning center, intended for students regularly enrolled in the academic year of course delivery https://talc.univr.it/it/competenze-trasversali
Booklet entry mode: the teaching is not expected to be included in the curriculum. Only after obtaining the Open Badge, the CFUs in the booklet will be automatically validated. The registration of CFUs in career is not instantaneous, but there will be some technical time to wait.
4. CONTAMINATION LAB
The Contamination Lab Verona (CLab Verona) is an experiential course with modules on innovation and enterprise culture that offers the opportunity to work in teams with students from all areas to solve challenges set by companies and organisations.
Upon completion of a CLab, students will be entitled to receive 6 CFU (D- or F-type credits).
Find out more: https://www.univr.it/clabverona
PLEASE NOTE: In order to be admitted to any teaching activities, including those of your choice, you must be enrolled in the academic year in which the activities in question are offered. Students who are about to graduate in the December and April sessions are therefore advised NOT to undertake extracurricular activities in the new academic year in which they are not enrolled, as these graduation sessions are valid for students enrolled in the previous academic year. Therefore, students who undertake an activity in an academic year in which they are not enrolled will not be granted CFU credits.
5. Stage/internship period
In addition to the CFUs required by the curriculum (check carefully what is indicated on the Didactic Regulations): here information on how to activate the internship.
Teachings and other activities that can be entered autonomously in the booklet
| years | Modules | TAF | Teacher |
|---|---|---|---|
| 1° 2° | Introduction to Robotics for students of scientific courses. | D |
Paolo Fiorini
(Coordinator)
|
| 1° 2° | Matlab-Simulink programming | D |
Bogdan Mihai Maris
(Coordinator)
|
| 1° 2° | Rapid prototyping on Arduino | D |
Franco Fummi
(Coordinator)
|
| 1° 2° | Programming Challanges | D |
Romeo Rizzi
(Coordinator)
|
| years | Modules | TAF | Teacher |
|---|---|---|---|
| 1° 2° | Introduction to 3D printing | D |
Franco Fummi
(Coordinator)
|
| 1° 2° | Python programming language | D |
Carlo Combi
(Coordinator)
|
| 1° 2° | HW components design on FPGA | D |
Franco Fummi
(Coordinator)
|
| 1° 2° | Protection of intangible assets (SW and invention)between industrial law and copyright | D |
Roberto Giacobazzi
(Coordinator)
|
| years | Modules | TAF | Teacher |
|---|---|---|---|
| 1° 2° | Federated learning from zero to hero | D |
Gloria Menegaz
|
Deep Learning (2022/2023)
Teaching code
4S009018
Credits
6
Language
English
Also offered in courses:
- Machine Learning & Deep Learning of the course Master's degree in Artificial intelligence
- Machine Learning & Deep Learning of the course Master's degree in Artificial intelligence
Scientific Disciplinary Sector (SSD)
INF/01 - INFORMATICS
The teaching is organized as follows:
Teoria
Laboratorio
Learning objectives
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.
Prerequisites and basic notions
Probability and Statistics
Image Processing
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
Bibliography
Didactic methods
The lessons will be in the presence, any supplementary material can be recovered from the video lessons of the previous year
Learning assessment procedures
The exam involves the discussion with the teacher of a written paper, which proposes a solution to an industrial classification problem. The grade will depend on the classification skills obtained by the classifier (with different measures of classification goodness from problem to problem), on the statistical confidence margins offered and on the theoretical motivation that prompted the student to choose a particular programming technique.
Evaluation criteria
Ability to face a recognition problem with the most appropriate tools. Ability to motivate implementation choices with theoretical notions. Ability to discuss results with interpretability
Criteria for the composition of the final grade
15/30 quality of the project. 15/30 capacity for appropriate discussion of the project itself
Exam language
Inglese
