SAILab

Gabriele Ciravegna (University of Siena) When: Mar 2nd, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Knowledge-driven Active Learning In the last few years, Deep Learning models have become increasingly popular. However, their deployment is still precluded in those contexts where the amount of supervised data is limited and manual labelling expensive. […]

Simone Marullo (University of Siena) When: Feb 16th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Optical Flow: history, state of the art and ongoing work The concept of optical flow, seen as a tool for motion detection and segmentation, has been of central importance in computer vision. Early algorithms are based […]

Veronica Lachi (University of Siena) When: Feb 9th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description A Mixed Statistical and Machine Learning approach for the Analysis of Multimodal Trail Making Test Data Eye-tracking can offer a novel clinical practice and a non-invasive tool to detect neuropathological syndromes. In this paper, we show […]

Caterina Graziani (University of Siena) When: Feb 2nd, 2022 – 11:45 – 12:30 AM Where: Google meet link Description Learning Representations over Dynamic Graphs Representation Learning over graph structured data has received significant attention recently due to its ubiquitous applicability. However, most advancements have been made in static graph settings while efforts for jointly learning […]

Giuseppe Alessio D’Inverno (University of Siena) When: Feb 2nd, 2022 – 11:00 – 11:45 AM Where: Google meet link Description The expressive power of Graph Neural Networks – A unifying point of view Graph Neural Networks (GNNs) are a wide class of connectionist models for graph processing. They perform an iterative message passing operation on […]

Lapo Faggi (University of Siena) When: Jan 19th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Learning invariant features from video streams: an optimal control approach Symmetries, invariances and conservation equations have always been an invaluable guide in Science to model natural phenomena through simple yet effective relations. For instance, in computer […]

Niccolò Pancino (University of Siena) When: Jan 12th, 2022 – 11:00 – 11:45 AM Where: Google meet link Description Using Domain-Specific Fingerprints Generated Through Neural Networks to Enhance Ligand-Based Virtual Screening by Janosch Menke and Oliver Koch Similarity-based virtual screening is a fundamental tool in the early drug discovery process and relies heavily on molecular […]

Enrico Meloni (University of Siena) When: Dec 22nd, 2021 – 11:00 – 11:45 AM Where: Google meet link Description AGENT: A Benchmark for Core Psychological Reasoning by Tianmin Shu et al For machine agents to successfully interact with humans in real-world settings, they will need to develop an understanding of human mental life. Intuitive psychology, […]

Marco Tanfoni (University of Siena) When: Dec 9th, 2021 – 11:00 – 11:45 AM Where: Google meet link Description Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains. Concept-based neural networks have arisen as explainable-by-design methods as they leverage human-understandable symbols (i.e. concepts) to predict class memberships. However, […]

Michele Casoni (University of Siena) When: Dec 9th, 2021 – 11:00 – 11:45 AM Where: Google meet link Description One of the most studied problems in the financial framework is how to find a combination of N assets, called Portfolio, which optimizes an investment objective. This problem is called “Portfolio Optimization Problem”. An optimal solution […]