73 citations · 85 across the 7 of their papers we have counts for
8 papers · 1 filter
The Impact of Stochasticity on the Rashomon Effect in Machine Learning
Andrea Apicella, Francesco Isgrò, Andrea Pollastro +1
Neural network training is inherently stochastic, with factors such as weight initialization leading to distinct models despite comparable predictive performance. This phenomenon i…
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…
Don't stop me now: How Validation Criteria Affect Checkpoint Selection and Early Stopping
Andrea Apicella, Francesco Isgrò, Andrea Pollastro +1
Checkpoint selection is a standard component of neural network training, yet the validation criterion used to select a checkpoint is often chosen heuristically. Moreover, the same…
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,…
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…
Towards a general framework for improving the performance of classifiers using XAI methods
Andrea Apicella, Salvatore Giugliano, Francesco Isgrò +1
Modern Artificial Intelligence (AI) systems, especially Deep Learning (DL) models, poses challenges in understanding their inner workings by AI researchers. eXplainable Artificial…
Don't Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning
Andrea Apicella, Francesco Isgrò, Roberto Prevete
Machine Learning (ML) has revolutionized various domains, offering predictive capabilities in several areas. However, with the increasing accessibility of ML tools, many practition…
Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers
Andrea Apicella, Francesco Isgrò, Roberto Prevete
In the context of classification problems, Deep Learning (DL) approaches represent state of art. Many DL approaches are based on variations of standard multi-layer feed-forward neu…