I use machine learning and statistical physics methods to address problems with large available datasets, and which involve a large number of interacting agents. I am also interested in the interaction between dynamics and energy / loss function landscape in systems with a large number of variables, ranging from toy models to deep neural networks.
[[ element.title ]]
We compare invasions in aquatic and terrestrial ecosystems primarily at large (national) spatial scales and among several higher-level taxa (insects, molluscs, crustaceans, all major vertebrate classes, and plants).
We test a big data workflow for understanding and predicting plankton dynamics using monitoring data.
Deep Neural Networks (DNNs) have shown empirical performance but they are still nevertheless a black-box function modeling data
Activated dynamics is a very slow process that takes place on exponentially large time scales. Usually it is associated to barrier hopping.
Community detection consists of extracting the affinity between agents of a system, which is extracted from quantities such as the frequency of interactions.