114 citations · 127 across the 2 of their papers we have counts for
2 papers
stat.ML2016★ 114 cited
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
Giorgio Patrini, Alessandro Rozza, Aditya Menon +2
We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss…
cs.LG2012★ 13 cited
DANCo: Dimensionality from Angle and Norm Concentration
Claudio Ceruti, Simone Bassis, Alessandro Rozza +3
In the last decades the estimation of the intrinsic dimensionality of a dataset has gained considerable importance. Despite the great deal of research work devoted to this task, mo…