Predicting long-term collective animal behavior with deep learning

Papaspyros, Vaios; Escobedo, Ramón; Alahi, Alexandre; Théraulaz, Guy; Sire, Clément; Mondada, Francesco

doi:10.1101/2023.02.15.528318

Cited by 3 publications

(26 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this work, we have exploited the fish data published in [25,60]. The fish are swimming in shallow water, and only their position and heading in the horizontal plane of the tank have been recorded so that the system is effectively 2-dimensional.…”

Section: Fish Trajectory Training Data Set Detailsmentioning

confidence: 99%

“…• Data availability: The data from [26,60] for N = 2 and N = 5 fish have been downsampled at 10 FPS and smoothed using a Gaussian kernel of width 0.15 s. The resulting fish trajectory time series are available at https://figshare.com/ projects/Data_and_Code_for_the_article_AI_without_networks/188349.…”

Section: Supplementary Informationmentioning

confidence: 99%

“…We have implemented the Hilbert interpolation scheme as a generative model by exploiting the experimental trajectories for N = 2 and N = 5 rummy-nose tetra fish (Hemigrammus rhodostomus) using previously published data [25,60]. Adult rummynose tetra, of typical body length 3-3.5 cm are social fish swimming in groups and can exhibit a highly coordinated behavior: highly polarized schools or vortex/milling schools.…”

Section: General Implementation Of the Hilbert Scheme In The Collecti...mentioning

confidence: 99%

See 2 more Smart Citations

AI without networks

Mitra,

Sire

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Contemporary Artificial Intelligence (AI) stands on two legs: large training data corpora and many-parameter artificial neural networks (ANNs). The data corpora are needed to represent the complexity and heterogeneity of the world. The role of the networks is less transparent due to the obscure dependence of the network parameters and outputs on the training data and inputs. This raises problems, ranging from technical-scientific to legal-ethical. We hypothesize that a transparent approach to machine learning is possible without using networks at all. By generalizing a parameter-free, statistically consistent data interpolation method, which we analyze theoretically in detail, we develop a framework for generative modeling. Given the growing usage of machine learning techniques in science, we demonstrate this framework with an example from the field of animal behavior. We applied this generative Hilbert framework to the trajectories of small groups of swimming fish. The framework outperforms previously developed state-of-the-art traditional mathematical behavioral models and contemporary ANN-based models in reproducing naturalistic behaviors. We do not suggest that the proposed framework will outperform networks in all applications, as over-parameterized networks can interpolate. However, our framework is theoretically sound, transparent, deterministic and parameter free: it does not require any compute-expensive training, does not involve optimization, has no model selection, and is easily reproduced and ported. We also propose an easily computed method of credit assignment based on this framework that could help address ethical-legal challenges raised by generative AI.

show abstract

Section: Fish Trajectory Training Data Set Detailsmentioning

confidence: 99%

Section: Supplementary Informationmentioning

confidence: 99%

Section: General Implementation Of the Hilbert Scheme In The Collecti...mentioning

confidence: 99%

See 1 more Smart Citation

AI without networks

Mitra,

Sire

2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Data accessibility. All the code concerning the data pre-processing, neural networks and plot scripts is publicly available from the Zenodo repository: https://doi.org/10.5281/zenodo.7634912 [51]. Experimental and generated data are available from the Zenodo repository: https://doi.org/10.…”

mentioning

confidence: 99%

“…Experimental and generated data are available from the Zenodo repository: https://doi.org/10. 5281/zenodo.7634687 [52].…”

mentioning

confidence: 99%

Predicting the long-term collective behaviour of fish pairs with deep learning

Papaspyros,

Escobedo,

Alahi

et al. 2024

J. R. Soc. Interface.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

AI Without Networks

Mitra,

Sire

2024

Preprint

View full text Add to dashboard Cite

Contemporary Artificial Intelligence (AI) stands on two legs: large training data corpora and many-parameter artificial neural networks (ANNs). The data corpora are needed to represent the complexity and heterogeneity of the world. The role of the networks is less transparent due to the obscure dependence of the network parameters and outputs on the training data and inputs. This raises problems, ranging from technical-scientific to legal-ethical. We hypothesize that a transparent approach to machine learning is possible without using networks at all. By generalizing a parameter-free, statistically consistent data interpolation method, which we analyze theoretically in detail, we develop a framework for generative modeling. Given the growing usage of machine learning techniques in science, we demonstrate this framework with an example from the field of animal behavior. We applied this generative Hilbert framework to the trajectories of small groups of swimming fish. The framework outperforms previously developed state-of-the-art traditional mathematical behavioral models and contemporary ANN-based models in reproducing naturalistic behaviors. We do not suggest that the proposed framework will outperform networks in all applications, as overparameterized networks can interpolate. However, our framework is theoretically sound, transparent, deterministic and parameter free: it does not require any compute-expensive training, does not involve optimization, has no model selection, and is easily reproduced and ported. We also propose an easily computed method of credit assignment based on this framework that could help address ethical-legal challenges raised by generative AI.

show abstract

Predicting long-term collective animal behavior with deep learning

Cited by 3 publications

References 48 publications

AI without networks

AI without networks

Predicting the long-term collective behaviour of fish pairs with deep learning

AI Without Networks

Contact Info

Product

Resources

About