Aggregated f -average Neural Network for Interpretable Ensembling - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2023

Aggregated f -average Neural Network for Interpretable Ensembling


Ensemble learning leverages multiple models (i.e., weak learners) on a common machine learning task to enhance prediction performance. Basic ensembling approaches average the weak learners outputs, while more sophisticated ones stack a machine learning model in between the weak learners outputs and the final prediction. This work fuses both aforementioned frameworks. We introduce an aggregated f-average (AFA) shallow neural network which models and combines different types of averages to perform an optimal aggregation of the weak learners predictions. We emphasise its interpretable architecture and simple training strategy, and illustrate its good performance on the problem of few-shot class incremental learning.
Fichier principal
Vignette du fichier
favg_tnnls.pdf (316.65 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04237149 , version 1 (11-10-2023)
hal-04237149 , version 2 (12-12-2023)




Mathieu Vu, Emilie Chouzenoux, Jean-Christophe Pesquet, Ismail Ben Ayed. Aggregated f -average Neural Network for Interpretable Ensembling. 2023. ⟨hal-04237149v2⟩
22 View
13 Download



Gmail Mastodon Facebook X LinkedIn More