Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Girardi, Ivan"'
Explanations are crucial parts of deep neural network (DNN) classifiers. In high stakes applications, faithful and robust explanations are important to understand and gain trust in DNN classifiers. However, recent work has shown that state-of-the-art
Externí odkaz:
http://arxiv.org/abs/2212.09155
Publikováno v:
International Conference on Learning Representations, 2022
State-of-the-art text classification models are becoming increasingly reliant on deep neural networks (DNNs). Due to their black-box nature, faithful and robust explanation methods need to accompany classifiers for deployment in real-life scenarios.
Externí odkaz:
http://arxiv.org/abs/2206.03178
Autor:
Girardi, Ivan, Vagenas, Panagiotis, Arcos-Díaz, Dario, Bessaï, Lydia, Büsser, Alexander, Furlan, Ludovico, Furlan, Raffaello, Gatti, Mauro, Giovannini, Andrea, Hoeven, Ellen, Marchiori, Chiara
We develop various AI models to predict hospitalization on a large (over 110$k$) cohort of COVID-19 positive-tested US patients, sourced from March 2020 to February 2021. Models range from Random Forest to Neural Network (NN) and Time Convolutional N
Externí odkaz:
http://arxiv.org/abs/2110.15002
Autor:
Marchiori, Chiara, Dykeman, Douglas, Girardi, Ivan, Ivankay, Adam, Thandiackal, Kevin, Zusag, Mario, Giovannini, Andrea, Karpati, Daniel, Saenz, Henri
Applying state-of-the-art machine learning and natural language processing on approximately one million of teleconsultation records, we developed a triage system, now certified and in use at the largest European telemedicine provider. The system eval
Externí odkaz:
http://arxiv.org/abs/2011.04548
Publikováno v:
Ivankay, Adam, Ivan Girardi, Chiara Marchiori, and Pascal Frossard. "FAR: A General Framework for Attributional Robustness." (2021). BMVC 2021
Attribution maps are popular tools for explaining neural networks predictions. By assigning an importance value to each input dimension that represents its impact towards the outcome, they give an intuitive explanation of the decision process. Howeve
Externí odkaz:
http://arxiv.org/abs/2010.07393
Autor:
Girardi, Ivan, Ji, Pengfei, Nguyen, An-phi, Hollenstein, Nora, Ivankay, Adam, Kuhn, Lorenz, Marchiori, Chiara, Zhang, Ce
We present an operational component of a real-world patient triage system. Given a specific patient presentation, the system is able to assess the level of medical urgency and issue the most appropriate recommendation in terms of best point of care a
Externí odkaz:
http://arxiv.org/abs/1809.10804
Publikováno v:
JHEP 08 (2014) 057
Models of neutrino mixing involving one or more sterile neutrinos have resurrected their importance in the light of recent cosmological data. In this case, reactor antineutrino experiments offer an ideal place to look for signatures of sterile neutri
Externí odkaz:
http://arxiv.org/abs/1405.6540
Publikováno v:
JHEP02 (2014) 050
We analyse the interplay of generalised CP transformations and the non-Abelian discrete group $T^{\prime}$ and use the semi-direct product $G_f= T^{\prime}\rtimes H_{\text{CP}}$, as family symmetry acting in the lepton sector. The family symmetry is
Externí odkaz:
http://arxiv.org/abs/1312.1966
Publikováno v:
JHEP 1311 (2013) 146
We investigate the predictions for neutrinoless double beta ($(\beta \beta)_{0 \nu}$-) decay effective Majorana mass $\left| \langle \, m \, \rangle \right|$ in the 3+1 and 3+2 schemes with one and two additional sterile neutrinos with masses at the
Externí odkaz:
http://arxiv.org/abs/1308.5802