no code implementations • 15 Aug 2023 • Honggui Li, Nahid Md Lokman Hossain, Maria Trocan, Dimitri Galayko, Mohamad Sawan
Five CMISR algorithms are respectively proposed based on the state-of-the-art open-loop MISR algorithms.
no code implementations • 20 Jan 2023 • Honggui Li, Maria Trocan, Mohamad Sawan, Dimitri Galayko
Closed-loop negative feedback mechanism is extensively utilized in automatic control systems and brings about extraordinary dynamic and static performance.
no code implementations • 19 Jul 2022 • Honggui Li, Maria Trocan, Dimitri Galayko, Mohamad Sawan
The proposed method depends on any existing approaches and upgrades their reconstruction performance by adding negative feedback structure.
no code implementations • 27 Jun 2022 • Guillaume Lachaud, Patricia Conde-Cespedes, Maria Trocan
We find that, in addition to requiring less preprocessing time, the classifiers trained on the datasets of patches selected based on entropy converge faster than on those selected based on the spectral similarity criterion and, furthermore, lead to higher accuracy.
no code implementations • 13 Nov 2021 • Adrien Bennetot, Ivan Donadello, Ayoub El Qadi, Mauro Dragoni, Thomas Frossard, Benedikt Wagner, Anna Saranti, Silvia Tulli, Maria Trocan, Raja Chatila, Andreas Holzinger, Artur d'Avila Garcez, Natalia Díaz-Rodríguez
Last years have been characterized by an upsurge of opaque automatic decision support systems, such as Deep Neural Networks (DNNs).
BIG-bench Machine Learning Explainable artificial intelligence +2
no code implementations • 29 Jun 2021 • Honggui Li, Dimitri Galayko, Maria Trocan, Mohamad Sawan
It is evaluated by the experimental results that the proposed autoencoders outperform the classical autoencoders in the performance of image reconstruction.
no code implementations • 15 Mar 2021 • Ayoub El Qadi, Natalia Diaz-Rodriguez, Maria Trocan, Thomas Frossard
We bring light by providing an expert-aligned feature relevance score highlighting the disagreement between a credit risk expert and a model feature attribution explanation in order to better quantify the convergence towards a better human-aligned decision making.