Training and Research
PhD Programme Courses/classes - 2024/2025
Advanced techniques for acquisition of biomedical images
Credits: 1
Language: Ingelese
Teacher: Pietro Bontempi, Federico Boschi
Algorithmic motion planning in robotics
Credits: 1
Language: Italian
Teacher: Paolo Fiorini
Brain Computer Interfaces
Credits: 3
Language: Inglese
Teacher: Silvia Francesca Storti
Data visualization
Credits: 1
Language: Italian
Teacher: Andrea Giachetti
Modelli di Intelligenza Artificiale Spiegabile: stato dell'arte, promesse e sfide
Credits: 2,5
Language: Inglese
Teacher: Gloria Menegaz
Foundation of Robotics Autonomy
Credits: 1
Language: Italian
Teacher: Paolo Fiorini
Generative AI
Credits: 1,5
Language: English
Teacher: Francesco Setti
Modellazione e analisi 3D
Credits: 1
Language: Italian
Teacher: Andrea Giachetti
Modellazione e verifica di sistemi digitali
Credits: 1,5
Language: Italian
Teacher: Franco Fummi, Nicola Bombieri, Graziano Pravadelli
Nanomaterials: synthesis, characterization and applications
Credits: 1
Language: English
Teacher: Francesco Enrichi
Soft robotics: from nature to engineering
Credits: 1,5
Language: Italian
Teacher: Francesco Visentin
Techniques and algorithms for biomechanics of movement
Credits: 2,5
Language: English
Teacher: Roberto Di Marco
Theranostics: from materials to devices
Credits: 1
Language: Italian
Teacher: Nicola Daldosso
Modelli di Intelligenza Artificiale Spiegabile: stato dell'arte, promesse e sfide (2024/2025)
Teacher
Referent
Credits
2.5
Language
Inglese
Class attendance
Free Choice
Location
VERONA
Learning objectives
Artificial Intelligence has become a fundamental instrument in fields like biomedicine and neurosciences, from the discovery of new numerical biomarkers to support to the diagnosis. In the last decades, large multidisciplinary collaborations and long-term multimodal studies as, e.g., ADNI, ENIGMA, and UK Biobank, made possible to access big repositories of different type of data like images and genetics information. Such an availability designates deep learning as particularly attractive to represent the complex relationships underlying many biological processes. However, despite the undeniable advantages of deep learning models like deep neural networks, the complexity of their architecture makes mandatory to obtain explanations favoring the interpretability, especially in medicine, healthcare and neuroscience fields. For this reason, the eXplainable Artificial Intelligence (XAI) is fundamental to explain how the model reached a specific outcome, how the features contributed, and to what extent the model is confident about the decision. This course aims at providing the students knowledge about the explainable models at the state of the art that are mostly exploited in the field, providing both theoretical bases and implementation tools. Especially, the students will learn how to deal with explainable AI when applied to interpret deep learning models assessed for extracting information from multi-dimensional heterogeneous and noisy data.
Prerequisites and basic notions
Fundamentals of signal and image processing, fundamentals of machine learning. Python.
Program
Program:
Part 1: Promises
• eXplainable Artificial Intelligence from scratch
• A hint into agnostic post-hoc explainability models (e.g. feature importance, occlusions)
• Neural networks in the light of explainability (e.g. visualization methods, attribution methods, gradient-based methods)
Part 2: Challenges
• Validation of XAI outcomes
Bibliography
When and where
In person.
Learning assessment procedures
Project related to the topics covered.
Assessment
Critical analysis of the methods learned
Ability to apply the methods learned to concrete problems Quality of presentation
Criteria for the composition of the final grade
Pass/Fail
PhD school courses/classes - 2024/2025
PhD School training offer to be defined
Faculty
Fiorini Paolo
PhD students
No people are present.
Loading...
Guidelines for PhD students
1. Distribution of ECTS per Year (60 CFU/year)
16 credits for coursework are allocated for the 1st and 2nd year, and 8 credits for coursework in the 3rd year, divided equally (50%) between the PhD Program (Intelligent Systems Engineering) and the University of Verona's Doctoral School. The remaining credits are for research (44 in the 1st and 2nd year, and 52 in the 3rd year).
- Coursework ECTS of the PhD Program in Intelligent Systems Engineering: These are obtained by participating in the educational activities provided by the PhD Program in Intelligent Systems Engineering or by attending Winter Schools or Summer Schools. Participation in Winter and Summer Schools for the purpose of earning coursework ECTS must be agreed upon with the tutor and the Coordinator. The PhD program’s educational activities can be found in the "Educational Offer of the Program" section on the program's web pages.
- Coursework ECTS of the University of Verona's Doctoral School: These are obtained by attending seminars and transversal courses, which can be found in the "Educational Offer of the School" section on the Program’s web pages. This category includes activities provided in other competence areas of the School according to Ministry provisions, such as language, computer, and statistical courses, courses on library resources, copyright, and other topics related to the organization and management of research. Some of these activities may only require passing an assessment (without attending the course) to earn the ECTS.
- Research ECTS: These are obtained by working on the research project, participating in "optional" training activities both at the PhD Program site and elsewhere, attending conferences as a speaker or listener, or through publications, etc. The activities undertaken must be listed in the PhD student's annual report. The composition of the research ECTS is at the discretion of the PhD student and the tutor. Research ECTS do not need to be formally (self)certified or checked by the Coordinator, as they are evaluated by the Academic Board as part of the PhD student's annual report.
2. Research Stays Abroad
The PhD study regulations stipulate that "The PhD student usually undertakes periods of research, training, and internships at public or private entities abroad." For students in the PhD Program in Intelligent Systems Engineering, it is strongly recommended to carry out a research period abroad of at least three months, preferably between the second and third year, in a context conducive to developing the PhD project. Funding for missions abroad can be obtained through various Erasmus calls (for study and internship) and the UniVR mobility call, in addition to the annual budget allocated for each PhD student and any external funds.
3. Verification of Achievement of Educational Objectives
The achievement of educational objectives for advancing to the next year and for confirming the scholarship (for the 1st and 2nd year) or admission to the final exam (3rd year) is verified based on the following activities and documentation:
- Completed coursework credits module (checked by the Coordinator).
- End-of-year report on the activities carried out by the PhD student, experiences gained, and skills acquired (approved by the tutor).
- Presentation to a subcommittee including at least two members in addition to the tutor (and co-tutor) of the research results obtained during the year.
- Report from the abovementioned subcommittee on the research activity carried out during the year.
4. Forms
The forms can be found on the University’s Intranet in the section:
"How to → PhDs → My Career as a PhD Student"