J
Jary Pomponi
Researcher at Sapienza University of Rome
Publications - 14
Citations - 182
Jary Pomponi is an academic researcher from Sapienza University of Rome. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 4, co-authored 10 publications receiving 45 citations.
Papers
More filters
Proceedings ArticleDOI
Avalanche: an End-to-End Library for Continual Learning
Vincenzo Lomonaco,Lorenzo Pellegrini,Andrea Cossu,Antonio Carta,Gabriele Graffieti,Tyler L. Hayes,Matthias De Lange,Marc Masana,Jary Pomponi,Gido M. van de Ven,Martin Mundt,Qi She,Keiland W. Cooper,Jeremy Forest,Eden Belouadah,Simone Calderara,German Ignacio Parisi,Fabio Cuzzolin,Andreas S. Tolias,Simone Scardapane,Luca Antiga,Subutai Ahmad,Adrian Popescu,Christopher Kanan,Joost van de Weijer,Tinne Tuytelaars,Davide Bacciu,Davide Maltoni +27 more
TL;DR: In this article, the authors propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch, which is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.
Journal ArticleDOI
Efficient continual learning in neural networks with embedding regularization
TL;DR: This work proposes a new, relatively simple and efficient method to perform continual learning by regularizing instead the network internal embeddings, and shows that this method performs favorably with respect to state-of-the-art approaches in the literature, while requiring significantly less space in memory and computational time.
Posted Content
Bayesian Neural Networks With Maximum Mean Discrepancy Regularization
TL;DR: In this paper, the authors propose a variant of the variational inference, where they replace the Kullback-Leibler divergence in the ELBO term with a Maximum Mean Discrepancy (MMD) estimator.
Journal ArticleDOI
DeepRICH: Learning Deeply Cherenkov Detectors.
C. Fanelli,Jary Pomponi +1 more
TL;DR: DeepRICH as mentioned in this paper is a deep learning algorithm for fast reconstruction which can be applied to different imaging Cherenkov detectors and leverages on a custom VAE combined to Maximum Mean Discrepancy (MMD), with a CNN extracting features from the space of the latent variables for classification.
Journal ArticleDOI
DeepRICH: learning deeply Cherenkov detectors
TL;DR: DeepRICH is a novel deep learning algorithm for fast reconstruction which can be applied to different imaging Cherenkov detectors and has the advantage to bypass low-level details needed to build a likelihood, allowing for a sensitive improvement in computation time at potentially the same reconstruction performance of other established reconstruction algorithms.