Carregant...
Fitxers
Tipus de document
ArticleVersió
Versió publicadaData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/218045
Predicting the generalization gap in neural networks using topological data analysis
Títol de la revista
Director/Tutor
ISSN de la revista
Títol del volum
Recurs relacionat
Resum
Understanding how neural networks generalize on unseen data is crucial for designing more robust and reliable models. In this paper, we study the generalization gap of neural networks using methods from topological data analysis. For this purpose, we compute homological persistence diagrams of weighted graphs constructed from neuron activation correlations after a training phase, aiming to capture patterns that are linked to the generalization capacity of the network. We compare the usefulness of different numerical summaries from persistence diagrams and show that a combination of some of them can accurately predict and partially explain the generalization gap without the need of a test set. Evaluation on two computer vision recognition tasks (CIFAR10 and SVHN) shows competitive generalization gap prediction when compared against state-of-the-art methods.
Matèries (anglès)
Citació
Citació
BALLESTER BAUTISTA, Rubén, ARNAL I CLEMENTE, Xavier, CASACUBERTA, Carles, MADADI, Meysam, CORNEANU, Ciprian adrian, ESCALERA GUERRERO, Sergio. Predicting the generalization gap in neural networks using topological data analysis. _Neurocomputing_. 2024. Vol. 596. [consulta: 21 de gener de 2026]. ISSN: 0925-2312. [Disponible a: https://hdl.handle.net/2445/218045]