Bio-inspired analysis of deep learning on not-so-big data using data-prototypes - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Frontiers in Computational Neuroscience Année : 2019

Bio-inspired analysis of deep learning on not-so-big data using data-prototypes

Thalita F Drumond
Thierry Viéville
Frédéric Alexandre

Résumé

Deep artificial neural networks are feed-forward architectures capable of very impressive performances in diverse domains. Indeed stacking multiple layers allows a hierarchical composition of local functions, providing efficient compact mappings. Compared to the brain, however, such architectures are closer to a single pipeline and require huge amounts of data, while concrete cases for either human or machine learning systems are often restricted to not-so-big data sets.Furthermore, interpretability of the obtained results is a key issue: since deep learning applications are increasingly present in society,it is important that the underlying processes be accessible and understandable to every one.In order to target these challenges, in this contribution we analyze how considering prototypes in a rather generalized sense (with respect to the state of the art)allows to reasonably work with small data sets while providing an interpretable view of the obtained results.Some mathematical interpretation of this proposal is discussed.Sensitivity to hyperparameters is a key issue for reproducible deep learning results, and is carefully considered in our methodology.Performances and limitations of the proposed setup are explored in details, under different hyperparameters sets, in an analogous way as biological experiments are conducted.We obtain a rather simple architecture, easy to explain, and which allows, combined with a standard method, to target both performances and interpretability.
Fichier principal
Vignette du fichier
pdf (8.28 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-01954911 , version 1 (12-10-2020)

Identifiants

Citer

Thalita F Drumond, Thierry Viéville, Frédéric Alexandre. Bio-inspired analysis of deep learning on not-so-big data using data-prototypes. Frontiers in Computational Neuroscience, 2019, 12, ⟨10.3389/fncom.2018.00100⟩. ⟨hal-01954911⟩
243 Consultations
33 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More