A dynamical system as the source of augmentation in a deep learning problem
Chaos, Solitons & Fractals: X · 2019
DOI: 10.1016/j.csfx.2019.100012 ↗Kurz gefasst
Fachartikel in der Zeitschrift Chaos, Solitons & Fractals: X, 2019. Verfasst von P.L. Tubaro und 1 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Richard Lounsbery Foundation.
Abstract (Originalsprache)
In this work we build a convolutional neural network capable of identifying individual birds by their songs. Since the actual data available from each individual is very limited, we use a dynamical system capable of synthesizing realistic songs, to generate surrogate-training data. The different synthetic songs are the result of integrating the dynamical system with slightly varied parameters. We show that a data set built in this way allows us to train the network to successfully identify the different individuals in our study. In this way, we present a novel way to perform data augmentation using dynamical systems.
Förderung
- Richard Lounsbery Foundation
Zitieren
APA
Tubaro, P., & Mindlin, G. (2019). A dynamical system as the source of augmentation in a deep learning problem. Chaos, Solitons & Fractals: X. https://doi.org/10.1016/j.csfx.2019.100012
Vancouver
Tubaro P, Mindlin G. A dynamical system as the source of augmentation in a deep learning problem. Chaos, Solitons & Fractals: X. 2019. doi:10.1016/j.csfx.2019.100012
BibTeX
@article{Tubaro2019,
author = {Tubaro, P.L. and Mindlin, G.B.},
title = {A dynamical system as the source of augmentation in a deep learning problem},
journal = {Chaos, Solitons & Fractals: X},
year = {2019},
doi = {10.1016/j.csfx.2019.100012}
}
EUVIMED