no code implementations • 15 Mar 2023 • Giorgia Adorni, Felix Boelter, Stefano Carlo Lambertenghi
In our work, we reproduce and evaluate a novel variation of the original GAN network, the GANformer, proposed in "Generative Adversarial Transformers" by Hudson and Zitnick.
1 code implementation • 25 Feb 2023 • Giorgia Adorni
These methods learn a controller by observing demonstrations of an expert, such as the behaviour of a centralised omniscient controller, which can perceive the entire environment, including the state and observations of all agents.
no code implementations • 23 Feb 2023 • Giorgia Adorni
In this way, we construct an embedding that contains the semantic information on the text, obtaining a kind of "geometry of meaning" in which concepts are translated into linear relationships.
no code implementations • 7 Sep 2022 • Francesca Mangili, Giorgia Adorni, Alberto Piatti, Claudio Bonesana, Alessandro Antonucci
Automatic assessment of learner competencies is a fundamental task in intelligent tutoring systems.
no code implementations • 24 Sep 2021 • Giorgia Adorni, Elia Cereda
In this project we trained a neural network to perform specific interactions between a robot and objects in the environment, through imitation learning.
no code implementations • 25 May 2021 • Alessandro Antonucci, Francesca Mangili, Claudio Bonesana, Giorgia Adorni
Graphical models, such as Bayesian networks, are used for adaptive tests as they allow to model the uncertainty about the questions and the skills in an explainable fashion, especially when coping with multiple skills.