4 papers
The Effect of Label Noise on the Information Content of Neural Representations
Ali Hussaini Umar, Franky Kevin Nando Tezoh, Jean Barbier +2
In supervised classification tasks, models are trained to predict a label for each data point. In real-world datasets, these labels are often noisy due to annotation errors. While…
Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime
Francesco Camilli, Daria Tieplova, Eleonora Bergamin +1
We rigorously analyse fully-trained neural networks of arbitrary depth in the Bayesian optimal setting in the so-called proportional scaling regime where the number of training sam…
Local bifurcation analysis of circular von-Kármán plate with Kirchhoff rod boundary
Deepankar Das, Basant Lal Sharma
Symmetry based reduction is applied to the buckling of a circular von-Karman plate with Kirchhoff rod boundary, where a mismatch between the edge length and the perimeter of plate…
Machine learning for cerebral blood vessels' malformations
Irem Topal, Alexander Cherevko, Yuri Bugay +5
Cerebral aneurysms and arteriovenous malformations are life-threatening hemodynamic pathologies of the brain. While surgical intervention is often essential to prevent fatal outcom…