no code implementations • 20 Dec 2023 • Eleonora Poeta, Gabriele Ciravegna, Eliana Pastor, Tania Cerquitelli, Elena Baralis
The field of explainable artificial intelligence emerged in response to the growing need for more transparent and reliable models.
no code implementations • 2 Oct 2023 • Flavio Giobergia, Alkis Koudounas, Elena Baralis
Exploring exoplanets has transformed our understanding of the universe by revealing many planetary systems that defy our current understanding.
no code implementations • 14 Sep 2023 • Eliana Pastor, Alkis Koudounas, Giuseppe Attanasio, Dirk Hovy, Elena Baralis
Existing work focuses on a few spoken language understanding (SLU) tasks, and explanations are difficult to interpret for most users.
1 code implementation • 14 Jun 2023 • Alkis Koudounas, Moreno La Quatra, Lorenzo Vaiani, Luca Colomba, Giuseppe Attanasio, Eliana Pastor, Luca Cagliero, Elena Baralis
Recent large-scale Spoken Language Understanding datasets focus predominantly on English and do not account for language-specific phenomena such as particular phonemes or words in different lects.
1 code implementation • Findings (ACL) 2022 • Giuseppe Attanasio, Debora Nozza, Dirk Hovy, Elena Baralis
EAR also reveals overfitting terms, i. e., terms most likely to induce bias, to help identify their effect on the model, task, and predictions.
1 code implementation • Applied Sciences 2021 • Simone Monaco, Salvatore Greco, Alessandro Farasin, Luca Colomba, Daniele Apiletti, Paolo Garza, Tania Cerquitelli, Elena Baralis
In this context, we analyze the burned area severity estimation problem by exploiting a state-of-the-art deep learning framework.
no code implementations • 17 Aug 2021 • Eliana Pastor, Luca de Alfaro, Elena Baralis
Furthermore, we quantify the contribution of all attributes in the data subgroup to the divergent behavior by means of Shapley values, thus allowing the identification of the most impacting attributes.
no code implementations • 18 Jul 2019 • Tania Cerquitelli, Stefano Proto, Francesco Ventura, Daniele Apiletti, Elena Baralis
To this aim, suitable automatic solutions to self-assess the prediction quality and the data distribution drift between the original training set and the new data have to be devised.
1 code implementation • IEEE AIKE 2019 • Andrea Pasini, Elena Baralis
This paper presents a semantic anomaly detection method (SAD) to detect anomalies in the predictions of any pixelwise semantic segmentation algorithm.
1 code implementation • 10 May 2018 • Luca Venturini, Elena Baralis, Paolo Garza
DAC exploits ensemble learning to distribute the training of an associative classifier among parallel workers and improve the final quality of the model.