AUTHOR=Ramezanian-Panahi Mahta , Abrevaya Germán , Gagnon-Audet Jean-Christophe , Voleti Vikram , Rish Irina , Dumas Guillaume TITLE=Generative Models of Brain Dynamics JOURNAL=Frontiers in Artificial Intelligence VOLUME=Volume 5 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2022.807406 DOI=10.3389/frai.2022.807406 ISSN=2624-8212 ABSTRACT=Biologically- and physically-informed models of neuronal dynamics have been advancing since the mid-twentieth century. Recent developments in artificial intelligence (AI) have accelerated this progress. This article gives an eagle-eye view of the recent, popular, and state-of-the-art advances in these models across different scales of organization and levels of abstraction. The studies reviewed in this paper include fundamental models in computational neuroscience, nonlinear dynamics, data-driven methods, as well as new promising frontiers. While not all of these models span the intersection of neuroscience, AI, and system dynamics, they have or can work in tandem as generative models. We discuss the limitations and unique dynamical traits of brain recordings, and the need for hypothesis- and data-driven modeling. While new biophysical discoveries unfold and new tools in scientific machine learning are being developed, the field needs hybrid methodologies for achieving interpretable, explainable, insightful, and efficient models of neural dynamics.