Preliminary Large-scale computer vision-based analysis of ant foraging dynamics enabled by novel mac

In my PhD, I want to build on these first results and to study in detail the factors which underlie the
ontogeny of task choices in individual ants, and how these choices result in behavioural patterns
observed at the level of the colony, in particular how the colony adjusts the size-distribution of their
foraging parties when feeding on food sources of different properties. To this end, I will continue the
development of versatile computer vision and machine learning tools. In particular, I will create
classifiers which allow the repeated identification of individuals across non-continuous recordings. The
training data required to power the deep learning algorithms behind this recognition will be provided
through a cooperation with the Zoological Garden in Wuppertal, Germany, which has already been set
up. We will conduct live experiments in the zoo, and encourage visitors to partake in data analysis.
Through this "citizen science" approach, we will be able to train and test our algorithms on an
unprecedented scale. The results of this project will provide novel insights into a fundamental biological
question - the adaptive advantage and hence evolution of division of labour in eusocial insects - using
modern engineering methods. Indeed, the models developed in this project will be versatile and
applicable in the analysis of various interactions between a large number of individuals.