How and why does deep ensemble coupled with transfer learning increase performance in bipolar disorder and schizophrenia classification? - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

How and why does deep ensemble coupled with transfer learning increase performance in bipolar disorder and schizophrenia classification?

Comment et pourquoi l'apprentissage par ensemble profond couplé à l'apprentissage par transfert améliore-t-il les performances de classification du trouble bipolaire et de la schizophrénie?

Résumé

Transfer learning (TL) and deep ensemble learning (DE) have recently been shown to outperform simple machine learning in classifying psychiatric disorders. However, there is still a lack of understanding as to why that is. This paper aims to understand how and why DE and TL reduce the variability of single-subject classification models in bipolar disorder (BD) and schizophrenia (SCZ). To this end, we investigated the training stability of TL and DE models. For the two classification tasks under consideration, we compared the results of multiple trainings with the same backbone but with different initializations. In this way, we take into account the epistemic uncertainty associated with the uncertainty in the estimation of the model parameters. It has been shown that the performance of classifiers can be significantly improved by using TL with DE. Based on these results, we investigate i) how many models are needed to benefit from the performance improvement of DE when classifying BD and SCZ from healthy controls, and ii) how TL induces better generalization, with and without DE. In the first case, we show that DE reaches a plateau when 10 models are included in the ensemble. In the second case, we find that using a pre-trained model constrains TL models with the same pre-training to stay in the same basin of the loss function. This is not the case for DL models with randomly initialized weights.
Fichier principal
Vignette du fichier
ISBI_paper_final_version.pdf (505.84 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04631924 , version 1 (02-07-2024)

Identifiants

  • HAL Id : hal-04631924 , version 1

Citer

Sara Petiton, Antoine Grigis, Benoit Dufumier, Edouard Duchesnay. How and why does deep ensemble coupled with transfer learning increase performance in bipolar disorder and schizophrenia classification?. ISBI 2024 - IEEE International Symposium on Biomedical Imaging, May 2024, Athenes, Greece. ⟨hal-04631924⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More