English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Collective movements are pervasive behaviours among social organisms and haveled to the development of many models. However, modelling animal trajectoriesand social interactions in simple bounded environments remains a challenge.Moreover, advances in the understanding of the sensory-motor loop and theinformation processing by animals are leading to revisions of the traditionalassumptions made in decision-making algorithms. In this context, we develop amethodology based on artificial neural networks (ANN) to describe thecollective motion of small zebrafish groups in a bounded environment. AlthoughANN models are commonly used in artificial systems they are stillunder-explored to model animal collective behaviours. Here, we present amethodology to calibrate Multilayer Perceptrons by learning from real fishexperimental data. The ANNs are trained using either supervised learning orvarious forms of evolutionary reinforcement learning methods (using the CMA-ESand NSGA-III algorithms). We reveal that ANN models trained using evolutionarymethods are capable of generating realistic collective motions for groups of 5zebrafish including the tank wall effects, a feature that is lacking inprevious models. Finally, we also discuss the benefits of optimised ANNs ascandidates for driving robotic lure with biologically realistic behaviour, amethod that is becoming increasingly popular to gather data and validateassumptions on collective behaviours.

Modelling zebrafish collective behaviours with multilayer perceptrons optimised by evolutionary algorithms