Simone Scardapane | Ricerc@Sapienza

Pubblicazioni

Titolo	Pubblicato in	Anno
Spatiotemporal graph neural network per energy forecasting e anomaly detection	Memorie ET2022	2022
A multimodal deep network for the reconstruction of T2W MR images	Progresses in Artificial Intelligence and Neural Systems	2021
Efficient data augmentation using graph imputation neural networks	Progresses in Artificial Intelligence and Neural Systems	2021
A wide multimodal dense U-net for fast magnetic resonance imaging	European signal processing conference	2021
Distributed training of graph convolutional networks	IEEE TRANSACTIONS ON SIGNAL AND INFORMATION PROCESSING OVER NETWORKS	2021
Bayesian Neural Networks with Maximum Mean Discrepancy regularization	NEUROCOMPUTING	2021
Flexible generative adversarial networks with non-parametric activation functions	Smart Innovation, Systems and Technologies	2021
A calibrated multiexit neural network for detecting urothelial cancer cells	COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE	2021
MARE: Self-supervised multi-attention REsu-net for semantic segmentation in remote sensing	REMOTE SENSING	2021
Structured ensembles. An approach to reduce the memory footprint of ensemble methods	NEURAL NETWORKS	2021
Avalanche. An end-to-end library for continual learning	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops	2021
Fairdrop. Biased edge dropout for enhancing fairness in graph representation learning	IEEE TRANSACTIONS ON ARTIFICIAL INTELLIGENCE	2021
Music genre classification using stacked auto-encoders	Smart Innovation, Systems and Technologies	2020
Optimized training and scalable implementation of Conditional Deep Neural Networks with early exits for Fog-supported IoT applications	INFORMATION SCIENCES	2020
Efficient continual learning in neural networks with embedding regularization	NEUROCOMPUTING	2020
Complex-valued neural networks with nonparametric activation functions	IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE	2020
Differentiable branching in deep networks for fast inference	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings	2020
Why should we add early exits to neural networks?	COGNITIVE COMPUTATION	2020
Adaptive propagation graph convolutional network	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS	2020
Missing data imputation with adversarially-trained graph convolutional networks	NEURAL NETWORKS	2020

ERC

PE6_7
PE6_11

KET

Big data & computing

Interessi di ricerca

My research focuses on machine and deep learning applied to audio, images, and graphs, and their deployment in distributed and decentralized environments, with a focus on edge machine learning, continual learning, and more. You can read more on my website: http://sscardapane.it/.

Keywords

machine learning

deep learning

Graph algorithms

Gruppi di ricerca

ISPAMM - Intelligent Signal Processing and MulitiMedia