no code implementations • 7 Aug 2021 • Leonardo Tanzi, Andrea Audisio, Giansalvo Cirrincione, Alessandro Aprato, Enrico Vezzetti
To demonstrate the reliability of this approach, 1) the attention maps were used to visualize the most relevant areas of the images, 2) the performance of a generic CNN and ViT was compared through unsupervised learning techniques, and 3) 11 specialists were asked to evaluate and classify 150 proximal femur fractures' images with and without the help of the ViT, then results were compared for potential improvement.
no code implementations • 6 Sep 2020 • Giansalvo Cirrincione, Pietro Barbiero, Gabriele Ciravegna, Vincenzo Randazzo
The former is just an adaptation of a standard competitive layer for deep clustering, while the latter is trained on the transposed matrix.
1 code implementation • 21 Aug 2020 • Pietro Barbiero, Gabriele Ciravegna, Vincenzo Randazzo, Giansalvo Cirrincione
The aim of this work is to present a novel comprehensive theory aspiring at bridging competitive learning with gradient-based learning, thus allowing the use of extremely powerful deep neural networks for feature extraction and projection combined with the remarkable flexibility and expressiveness of competitive learning.
1 code implementation • Neural Networks 2020 • Giansalvo Cirrincione, Gabriele Ciravegna, Pietro Barbiero, Vincenzo Randazzo, Eros Pasero
Furthermore, an important and very promising application of GH-EXIN in two-way hierarchical clustering, for the analysis of gene expression data in the study of the colorectal cancer is described.