We introduce an approach which allows inferring causal relationships bet...
Transformers are the type of neural networks that has revolutionised nat...
Transfer learning is a powerful tool enabling model training with limite...
Large transformers are powerful architectures for self-supervised analys...
Real world-datasets characterized by discrete features are ubiquitous: f...
Visual object recognition has been extensively studied in both neuroscie...
DADApy is a python software package for analysing and characterising
hig...
Deep neural networks (DNNs) defy the classical bias-variance trade-off:
...
Real-world data typically contain a large number of features that are of...
Modern datasets are characterized by a large number of features that may...
We apply two independent data analysis methodologies to locate stable cl...
Deep convolutional networks (DCNs) learn meaningful representations wher...
Deep neural networks progressively transform their inputs across multipl...
It is well known that a small number of variables is often sufficient to...
Analyzing large volumes of high-dimensional data is an issue of fundamen...
Data analysis in high-dimensional spaces aims at obtaining a synthetic
d...