Amb motiu del tancament d'estiu, la validació de documents es reprendrà a partir del 28 d'agost de 2026. Disculpeu les molèsties.
Con motivo del cierre de verano, la validación de documentos se reanudará a partir del 28 de agosto de 2026. Disculpad las molestias
Due to the summer closure, document validation will resume starting August 28, 2026. We apologize for any inconvenience.

Files

859689.pdf (2.54 MB)

Document type

Article

Version

Published version

Publication date

2024-09-01

Publication license

cc-by (c) Rubén Ballester Bautista et al., 2024
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/218045

Predicting the generalization gap in neural networks using topological data analysis

Journal Title

Authors

Director/Tutor

Journal ISSN

Volume Title

Related resource

https://doi.org/10.1016/j.neucom.2024.127787

Abstract

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.

Subject

Topologia, Aprenentatge automàtic, Xarxes neuronals (Informàtica)

Subject (English)

Topology, Machine learning, Neural networks (Computer science)

Citation

Collections

Articles publicats en revistes (Matemàtiques i Informàtica)

Citation

BALLESTER BAUTISTA, Rubén, et al. Predicting the generalization gap in neural networks using topological data analysis. Neurocomputing. 2024. Vol. 596. ISSN 0925-2312. [consulted: 9 of August of 2026]. Available at: https://hdl.handle.net/2445/218045

Export metadata

JSON - METS

Share record