5 papers · 1 filter
Instance-Adaptive Parametrization for Amortized Variational Inference
Andrea Pollastro, Andrea Apicella, Francesco Isgrò +1
Variational autoencoders (VAEs) rely on amortized variational inference to enable efficient posterior approximation, but this efficiency comes at the cost of a shared parametrizati…
IMPACTX: improving model performance by appropriately constraining the training with teacher explanations
Andrea Apicella, Salvatore Giugliano, Francesco Isgrò +2
The eXplainable Artificial Intelligence (XAI) research predominantly concentrates to provide explainations about AI model decisions, especially Deep Learning (DL) models. However,…
Don't stop me now: Rethinking Validation Criteria for Model Parameter Selection
Andrea Apicella, Francesco Isgrò, Andrea Pollastro +1
Despite the extensive literature on training loss functions, the evaluation of generalization on the validation set remains underexplored. In this work, we conduct a systematic emp…
SincVAE: A new semi-supervised approach to improve anomaly detection on EEG data using SincNet and variational autoencoder
Andrea Pollastro, Francesco Isgrò, Roberto Prevete
Over the past few decades, electroencephalography (EEG) monitoring has become a pivotal tool for diagnosing neurological disorders, particularly for detecting seizures. Epilepsy, o…
Toward the application of XAI methods in EEG-based systems
Andrea Apicella, Francesco Isgrò, Andrea Pollastro +1
An interesting case of the well-known Dataset Shift Problem is the classification of Electroencephalogram (EEG) signals in the context of Brain-Computer Interface (BCI). The non-st…