Simone Marullo (University of Siena) When: Oct 20th, 2021 – 11:00 – 11:45 AM Where: Google meet link Description Designing agents that autonomously learn in a visual environment is not that easy, since standard supervised offline strategies are not available. We want to discuss novel techniques, exploiting a human-like attention mechanism both for learning and […]

Giuseppe Alessio D’Inverno (University of Siena) When: Oct 13th, 2021 – 11:00 – 11:45 AM Where: Google meet link Description Conventional reduced order modeling techniques such as the reduced basis (RB) method (relying, e.g., on proper orthogonal decomposition (POD)) may incur in severe limita- tions when dealing with nonlinear time-dependent parametrized PDEs, as these are […]

Veronica Lachi (University of Siena) When: Oct 5th, 2021 – 11:00 – 11:45 AM Where: Google meet link Description We introduce a new family of deep neural network models. Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network. The output of the network […]

Caterina Graziani (University of Siena) When: Sep 29th, 2021 – 11:00 – 11:45 AM Where: Google meet link Description Neuro-symbolic methods integrate neural architectures, knowledge representation and reasoning. However, they have been struggling at both dealing with the intrinsic uncertainty of the observations and scaling to real world applications. This paper presents Relational Reasoning Networks […]

Nicola Picchiotti (University of Pavia) When: Sep 22nd, 2021 – 11:00 – 11:45 AM Where: Google meet link Description The “black box” nature of deep neural network models is often a limit for safe applications since the reliability of the model predictions can be affected by the incompleteness in the optimization problem formalization. To frame […]

Gabriele Ciravegna (University of Siena) When: Sep 8th, 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, […]

Anna Visibelli (University of Siena) When: Sep 1st, 2021 – 11:00 – 11:45 AM Where: Google meet link Description By: Edison Ong, Haihe Wang, Mei U Wong, Meenakshi Seetharaman, Ninotchka Valdez and Yongqun He. Reverse vaccinology (RV) is a milestone in rational vaccine design, and machine learning (ML) has been applied to enhance the accuracy […]

Luca Pasqualini (University of Siena) When: Jul 27th, 2021 – 11:00 – 11:45 AM Where: Google meet link Description In reinforcement learning, with the exception of some control problems, de-facto continuous action spaces are rare. They have a powerful feature though: they can be used to reduce the complexity of combinatorial discrete action spaces. Through […]

Giorgio Ciano (University of Siena) When: Jul 21st, 2021 – 11:00 – 11:45 AM Where: Google meet link Description Computer-aided diagnosis (CAD) of prostate cancer (PCa) using multiparametric magnetic resonance imaging (mpMRI) is actively being investigated as a means to provide clinical decision support to radiologists. Typically, these sy tems are trained using lesion annotations. […]

Lapo Faggi (University of Florence) When: Jul 14th, 2021 – 11:00 – 11:45 AM Where: Google meet link Description Traditional machine learning techniques usually assume static input data and the existence of a neat distinction between a training and a test phase. Input data, entirely available at the beginning of the learning procedure, are processed […]