37 citations · 108 across the 10 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2021
Persistent Homology Captures the Generalization of Neural Networks Without A Validation Set
Asier Gutiérrez-Fandiño, David Pérez-Fernández, Jordi Armengol-Estapé +1
The training of neural networks is usually monitored with a validation (holdout) set to estimate the generalization of the model. This is done instead of measuring intrinsic proper…
cs.LG2021
Characterizing and Measuring the Similarity of Neural Networks with Persistent Homology
David Pérez-Fernández, Asier Gutiérrez-Fandiño, Jordi Armengol-Estapé +1
Characterizing the structural properties of neural networks is crucial yet poorly understood, and there are no well-established similarity measures between networks. In this work,…