5 papers
A general approach to compute the relevance of middle-level input features
Andrea Apicella, Salvatore Giugliano, Francesco Isgrò +1
This work proposes a novel general framework, in the context of eXplainable Artificial Intelligence (XAI), to construct explanations for the behaviour of Machine Learning (ML) mode…
A survey on modern trainable activation functions
Andrea Apicella, Francesco Donnarumma, Francesco Isgrò +1
In neural networks literature, there is a strong interest in identifying and defining activation functions which can improve neural network performance. In recent years there has b…
Contributions to the 36th International Cosmic Ray Conference (ICRC 2019) of the JEM-EUSO Collaboration
G. Abdellaoui, S. Abe, J. H. Adams +309
Compilation of papers presented by the JEM-EUSO Collaboration at the 36th International Cosmic Ray Conference (ICRC), held July 24 through August 1, 2019 in Madison, Wisconsin.
A simple and efficient architecture for trainable activation functions
Andrea Apicella, Francesco Isgrò, Roberto Prevete
Learning automatically the best activation function for the task is an active topic in neural network research. At the moment, despite promising results, it is still difficult to d…
First observations of speed of light tracks by a fluorescence detector looking down on the atmosphere
G. Abdellaoui, S. Abe, J. H. Adams +311
EUSO-Balloon is a pathfinder mission for the Extreme Universe Space Observatory onboard the Japanese Experiment Module (JEM-EUSO). It was launched on the moonless night of the 25$^…