AI @ Roma Tre
The AI program at Roma Tre University comprises a multidisciplinary group of researchers conducting investigations on methods and tools for intelligent system development. The research activity of the AI laboratory embraces both formal approaches and theoretically grounded investigations, exploration and empirical-experimental techniques.
The group is part of the Department of Civil Engineering, Computer Science and Aeronautical Technologies (former Department of Engineering), which has been selected by the Minister of Education, University and Research (MIUR) as one of the “Department of Excellence” 2018-2022.
In 2017 two faculty members of the laboratory joined the A.I. Task Force promoted by Agency for Digital Italy (AgID), the technical agency of the Presidency of the Italian Council of Ministers. The task force’s focus is identifying AI solutions for public services to improve the relationship between public administrations and citizens.
Since 2018 the AI laboratory is active node of the national Laboratory of Artificial Intelligence and Intelligent Systems (AIIS) of CINI (National Interuniversity Consortium for Informatics).
Four courses that provide an AI specialization to help students master skills such as Machine Learning, Deep Learning, AI Logics, Planning and recent advances in Intelligent systems for Internet.
Investigation of new methodologies to solve specific, practical and present-day problems, with experiments on real-world case studies, with the support of GPU-based computing architecture (multi-GPU NVidia Tesla).
Critical interactions between science and business, within strategic frameworks that include cooperation in education, training and technology transfer to ensure the transition of research results.
Community Engaged Research
Active role in editorial boards of International journal, member of program committees of international conferences, organization of seminars and meetings.
Marta Cialdea Mayer
PhD, Associate Professor
PhD, Associate Professor
PhD, Assistant Professor
PhD, Assistant Professor
Other scholars, principal collaborators and PhD students
The goal is to present the fundamental models, methods and techniques of various areas of Artificial Intelligence, with particular reference to heuristic search, knowledge representation and automatic reasoning, machine learning, natural language processing, computer vision. The lessons and practical exercises carried out during the course will allow the student to acquire analytical and problem solving skills on various domains of interest for the discipline.
A course for describing the problems relative to the study, realization and experimentation of software systems for the Internet, realized by means of Artificial Intelligence techniques. The focus is on the adaptive systems based on user modeling. Scheduled on 1st semester of 2nd year in the Master degree of Engineering in Computer Science.
It provides the foundamental knowledge of classical and some non-classical logics and some of their applications in computer science. Scheduled on 2nd semester of 1st year in the Master degree of Engineering in Computer Science.
It enables students to deepen the main Machine Learning models and methods, such as Regression, Classification, Clustering, Deep Learning, and use them as tools for the development of innovative technologies. Scheduled on 2nd semester of 1st year in the Master degree of Engineering in Computer Science.
It introduces models and resolution techniques for both “classic” and temporal planning, involving scheduling aspects. Different methodologies for the synthesis of action plans and their execution will be
presented, as well as aspects related to automated learning of classical planning domains. Some applications and samples will be presented and discussed, also in relation to the control of autonomous robots. Scheduled on 1st semester of 2nd year in the Master degree of Engineering in Computer Science.
The course consists of a theoretical part on the fundamental concepts, and laboratory activities in which DL concepts are applied and developed through a software framework. At the end of the course the student will be able to: adequately train and optimize Deep neural networks; distinguish between different solutions and be able to choose and customize the most effective architectures in real-world scenarios: supervised, unsupervised or following a reinforcement learning approach. Scheduled on 1st semester of 2nd year in the Master degree of Engineering in Computer Science.
It introduces formal tools to model strategic interactions between two or more players, typically rational individuals who make decisions in order to optimize their subjective goals. During the course, cooperative and non-cooperative games will be studied, starting from applications in the social, political or economic fields, to arrive at applications in various fields of artificial intelligence, from the training of neural networks to reinforcement learning in multi-agent systems.
It focuses on applications of AI and ML in the engineering and artistic fields. The course is therefore designed in two parts: the first concerns AI applications to electrical energy and information engineering; the second focuses on the use of ML techniques for musical and artistic production in general. Scheduled on 2nd semester of 2nd year in the Master degree of Engineering in Computer Science.
It presents the main theoretical and methodological tools for modeling decisions and for identifying the best decision support strategies. It provides the skills on how to use the available data in analytical prescriptive models, how to read the results provided by the adopted models and how to interpret them to propose appropriate solutions to complex management problems. Scheduled on 1st semester of 2nd year in the Master degree of Engineering in Computer Science.
- Discovering prerequisite relations from educational documents through word embeddings (Gasparetti, Fabio), In Future Generation Computer Systems, 2021.
- Community detection in social recommender systems: a survey (Gasparetti, Fabio and Sansonetti, Giuseppe and Micarelli, Alessandro), In Applied Intelligence, volume 51, 2021.
- An Empirical Review of Automated Machine Learning (Vaccaro, Lorenzo, Sansonetti, Giuseppe and Micarelli, Alessandro), In Computers, volume 10, 2021.
- Unreliable Users Detection in Social Media (Sansonetti, Giuseppe and Gasparetti, Fabio and D’Aniello, Giuseppe and Micarelli, Alessandro), In IEEE Access, volume 8, 2020.
- MoodleREC: A recommendation system for creating courses using the moodle e-learning platform (Carlo De Medio, Carla Limongelli, Filippo Sciarrone and Marco Temperini), In Comput. Hum. Behav., volume 104, 2020.
- Personalized weight loss strategies by mining activity tracker data (Gasparetti, Fabio, Aiello, Luca Maria and Quercia, Daniele), In User Modeling and User-Adapted Interaction, 2019.
- Cross-domain recommendation for enhancing cultural heritage experience (Sansonetti, G., Gasparetti, F. and Micarelli, A.), In ACM UMAP 2019 Adjunct – Adjunct Publication of the 27th Conference on User Modeling, Adaptation and Personalization, 2019.
- Point of interest recommendation based on social and linked open data (Sansonetti, G.), In Personal and Ubiquitous Computing, volume 23, 2019.
- BERT, ELMo, use and infersent sentence encoders: The Panacea for research-paper recommendation? (Mohamed Hassan, H.A., Sansonetti, G., Gasparetti, F., Micarelli, A. and Beel, J.), In Proceedings of ACM RecSys 2019 Late-breaking Results co-located with the 13th ACM Conference on Recommender Systems (RecSys 2019), volume 2431, 2019.
- Exploiting semantics for context-aware itinerary recommendation (Fogli, A. and Sansonetti, G.), In Personal and Ubiquitous Computing, volume 23, 2019.