How I Learned to Stop Worrying and Start Loving NeuroAI

A central goal of neuroscience is understanding how neural circuits transform sensory input into the behavior animals use to survive in a dynamic world. Progress has been limited less by a shortage of data than by our ability to measure, model, and integrate it: behavior has long resisted quantification despite being the ultimate output of the nervous system. Data-driven AI is changing this. Deep learning can now extract fine-grained behavioral kinematics from raw video at scale, turning behavior into a rich dataset on par with large-scale neural recordings and connectomes. We argue the next opportunity is using AI not just to measure these signals but to model the system linking them. We discuss an emerging class of approaches using artificial neural networks as models of biological neural systems, jointly capturing interactions between circuits, bodies, physics, and behavior. By incorporating the biomechanical intelligence embedded in physical bodies, these models bridge the functional gaps between environmental stimuli, neural activity, and behavioral output—gaps no single experimental paradigm can span alone. Such models are also generative: they can simulate novel conditions, predict perturbation consequences, and produce testable mechanistic hypotheses. The resulting experiments yield data that refine the models in turn, establishing a flywheel between data-driven AI and experimental neuroscience.