1

A round-trip journey in pruned artificial neural networks
In the last decade, deep learning models competed for performance at the price of tremendous computational costs. Such a critical …
Cite URL
Artificial intelligence methods for biomedical imaging and omics data
The use of deep learning in biomedical imaging and omics data has shown great potential for enhancing medical diagnosis and improving …
Cite URL
Fairness, Debiasing and Privacy in Computer Vision and Medical Imaging
Deep Learning (DL) has become one of the predominant tools for solving a variety of issue, often with superior performance compared to …
Cite URL
Shannon Strikes Again! Entropy-based Pruning in Deep Neural Networks for Transfer Learning under Extreme Memory and Computation Budgets
Deep neural networks have become the de-facto standard across various computer science domains. Nonetheless, effectively training these …
Cite DOI URL
Study of historical Byzantine seal images: the BHAI project for computer-based sigillography
BHAI 1 (Byzantine Hybrid Artificial Intelligence) is the first project based on artificial intelligence dedicated to Byzantine seals. …
Cite DOI URL
UNBIASED SUPERVISED CONTRASTIVE LEARNING
Many datasets are biased, namely they contain easy-to-learn features that are highly correlated with the target class only in the …
Cite URL
To update or not to update? Neurons at equilibrium in deep models
Recent advances in deep learning optimization showed that, with some a-posteriori information on fully-trained models, it is possible …
Cite URL
TOWARDS EFFICIENT CAPSULE NETWORKS
From the moment Neural Networks dominated the scene for image processing, the computational complexity needed to solve the targeted …
Cite DOI URL
Bridging the gap between debiasing and privacy for deep learning
The broad availability of computational resources and the recent scientific progresses made deep learning the elected class of …
Cite DOI URL
End: Entangling and Disentangling deep representations for bias correction
Artificial neural networks perform state-of-the-art in an ever-growing number of tasks, and nowadays they are used to solve an …
Cite DOI URL