24 citations · 73 across the 15 of their papers we have counts for
4 papers · 1 filter
Unveiling Transformer Perception by Exploring Input Manifolds
Alessandro Benfenati, Alfio Ferrara, Alessio Marta +2
This paper introduces a general method for the exploration of equivalence classes in the input space of Transformer models. The proposed approach is based on sound mathematical the…
Majorization-Minimization for sparse SVMs
Alessandro Benfenati, Emilie Chouzenoux, Giorgia Franchini +5
Several decades ago, Support Vector Machines (SVMs) were introduced for performing binary classification tasks, under a supervised framework. Nowadays, they often outperform other…
A singular Riemannian geometry approach to Deep Neural Networks I. Theoretical foundations
Alessandro Benfenati, Alessio Marta
Deep Neural Networks are widely used for solving complex problems in several scientific areas, such as speech recognition, machine translation, image analysis. The strategies emplo…
A singular Riemannian geometry approach to Deep Neural Networks II. Reconstruction of 1-D equivalence classes
Alessandro Benfenati, Alessio Marta
In a previous work, we proposed a geometric framework to study a deep neural network, seen as sequence of maps between manifolds, employing singular Riemannian geometry. In this pa…