Alessandro Sebastian Russo

Ph.D. candidate in Ingegneria Informatica E Dei Sistemi , 38^th cycle (2022-2025)
Department of Control and Computer Engineering (DAUIN)

Docente esterno e/o collaboratore didattico
Department of Control and Computer Engineering (DAUIN)

alessandro.russo@polito.it

Profile

PhD

Research topic

Scalable architectures for neural-symbolic scene interpretation and generation

Tutors

Research presentation

Poster

Research interests

Data science, Computer vision and AI

Biography

I am currently part of the GRAINS group at DAUIN Politecnico di Torino. I completed my Master's degree in Data Science at Politecnico di Torino in 2021, focusing my thesis on Machine Learning and Computer Vision and Transformer Neural Networks. After a short one-year research grant, during which I was able to hone my skills and further develop my knowledge of machine learning methods in the medical setting, I enrolled as a 38th cycle PhD student at Politecnico di Torino. For my research goal, I decided to dive into Neuro-Symbolic AI, focusing on its application to the Scene Graph Generation (SGG) task. My work aims to combine the capabilities of neural networks with symbolic reasoning to improve scene understanding, enabling more accurate and less biased SGG models. By utilizing the Logic Tensor Networks (LTN) and combining it with state-of-the-art SGG methods, my current contributions have led to the creation of models that can generate semantically richer scene graphs in areas such as autonomous driving, proving their utility for advanced applications in computer vision and robotics. I am currently exploring techniques to improve SGG models on a broader scale. I am using methods that utilize Large Language Models (LLMs) and Commonsense Knowledge Bases (CSKB) such as ConceptNet to automatically extract common sense prior knowledge that can be used to improve the logical consistency and variability of predictions in scene understanding tasks.

Teaching

Teachings

Master of Science

Mobile application development. A.A. 2024/25, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso
Gestione dell'innovazione e sviluppo prodotto ICT. A.A. 2023/24, INGEGNERIA GESTIONALE. Collaboratore del corso
Mobile application development. A.A. 2022/23, INGEGNERIA INFORMATICA (COMPUTER ENGINEERING). Collaboratore del corso

MostraNascondi A.A. passati

Publications

Latest publications View all publications in Porto@Iris

Manigrasso, Francesco; Milazzo, Rosario; Russo, Alessandro; Lamberti, Fabrizio; Strand, ... (2025)
Mammography classification with multi-view deep learning techniques: investigating graph and transformer-based architectures. In: MEDICAL IMAGE ANALYSIS, vol. 99. ISSN 1361-8415
Contributo su Rivista
Russo, Alessandro; Morra, Lia; Lamberti, Fabrizio; Dimasi, PAOLO EMMANUEL ILARIO (2024)
ESRA: A Neuro-Symbolic Relation Transformer for Autonomous Driving. In: International Joint Conference on Neural Networks (IJCNN) 2024, Yokohama (JPN), 30 June 2024 - 05 July 2024. ISBN: 979-8-3503-5931-2
Contributo in Atti di Convegno (Proceeding)
Piano, Luca; Manigrasso, Francesco; Russo, Alessandro; Morra, Lia (2024)
Enhancing Neuro-Symbolic Integration with Focal Loss: A Study on Logic Tensor Networks. In: 18th International Conference on Neuro-symbolic Learning and Reasoning, Barcelona (ESP), September 9–12, 2024, pp. 14-23. ISSN 0302-9743. ISBN: 978-3-031-71169-5
Contributo in Atti di Convegno (Proceeding)
Russo, Alessandro; Manigrasso, Francesco; Lamberti, Fabrizio; Morra, Lia (2023)
L-TReiD: Logic Tensor Transformer for Re-Identification. In: International Symposium on Visual Computing (ISVC) 2023, Lake Tahoe, Nevada, USA, 16/10/2023 - 18/10/2023, pp. 345-357. ISSN 0302-9743. ISBN: 978-3-031-47965-6
Contributo in Atti di Convegno (Proceeding)
Morra, Lia; Azzari, Alberto; Bergamasco, Letizia; Braga, Marco; Capogrosso, Luigi; ... (2023)
Designing Logic Tensor Networks for Visual Sudoku puzzle classification. In: 17th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy 2023), Certosa di Pontignano, Siena (Italia), July 3-5, 2023, pp. 223-232. ISSN 1613-0073
Contributo in Atti di Convegno (Proceeding)

Society and Enterprise

Patents and other intellectual properties

Deep Neural Networks For Multi-View Mammography Classification. national Patent
Inventors: Francesco Manigrasso Rosario Milazzo Lia Morra Alessandro Sebastian Russo