Predicting the long-term collective behaviour of fish pairs with deep learning
Journal of The Royal Society Interface · 2024
DOI: 10.1098/rsif.2023.0630 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of The Royal Society Interface, 2024. Verfasst von Vaios Papaspyros und 5 weiteren Autor:innen. Beteiligte Einrichtung: Mobile Robotic Systems (Mobots) group, Institute of Electrical and Micro Engineering, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausan…. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agence Nationale de la Recherche, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung, Indo-French Centre for the Promotion of Advanced Research.
Abstract (Originalsprache)
Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social interactions in the fish species Hemigrammus rhodostomus . We compare the results of our deep learning approach with experiments and with the results of a state-of-the-art analytical model. To that end, we propose a systematic methodology to assess the faithfulness of a collective motion model, exploiting a set of stringent individual and collective spatio-temporal observables. We demonstrate that machine learning (ML) models of social interactions can directly compete with their analytical counterparts in reproducing subtle experimental observables. Moreover, this work emphasizes the need for consistent validation across different timescales, and identifies key design aspects that enable our deep learning approach to capture both short- and long-term dynamics. We also show that our approach can be extended to larger groups without any retraining, and to other fish species, while retaining the same architecture of the deep learning network. Finally, we discuss the added value of ML in the context of the study of collective motion in animal groups and its potential as a complementary approach to analytical models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Mobile Robotic Systems (Mobots) group, Institute of Electrical and Micro Engineering, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland.
- Centre de Recherches sur la Cognition Animale, Centre de Biologie Intégrative, CNRS, Université de Toulouse III - Paul Sabatier, 31062 Toulouse, France.
- VITA group, Civil Engineering Institute, École Polytechnique Fédérale de Lausanne (EPFL), CH-1015 Lausanne, Switzerland.
- Laboratoire de Physique Théorique, CNRS, Université de Toulouse III - Paul Sabatier, 31062 Toulouse, France.
ORCID-Profile: Vaios Papaspyros, Ramón Escobedo, Alexandre Alahi, Guy Theraulaz, Clément Sire, Francesco Mondada
Förderung
- Agence Nationale de la Recherche
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Indo-French Centre for the Promotion of Advanced Research
Zitieren
APA
Papaspyros, V., Escobedo, R., Alahi, A., Theraulaz, G., Sire, C., & Mondada, F. (2024). Predicting the long-term collective behaviour of fish pairs with deep learning. Journal of The Royal Society Interface. https://doi.org/10.1098/rsif.2023.0630
Vancouver
Papaspyros V, Escobedo R, Alahi A, Theraulaz G, Sire C, Mondada F. Predicting the long-term collective behaviour of fish pairs with deep learning. Journal of The Royal Society Interface. 2024. doi:10.1098/rsif.2023.0630
BibTeX
@article{Papaspyros2024,
author = {Papaspyros, Vaios and Escobedo, Ramón and Alahi, Alexandre and Theraulaz, Guy and Sire, Clément and Mondada, Francesco},
title = {Predicting the long-term collective behaviour of fish pairs with deep learning},
journal = {Journal of The Royal Society Interface},
year = {2024},
doi = {10.1098/rsif.2023.0630}
}
EUVIMED