Work of Sani et al. (open access) is reported in the Oct. 2024 issue of Nature Neuroscience. From the editor's summary:
Neural dynamics are complex and simultaneously relate to distinct behaviors. To address these challenges, Sani et al. have developed an AI framework termed DPAD that achieves nonlinear dynamical modeling of neural–behavioral data, dissociates behaviorally relevant neural dynamics, and localizes the source of nonlinearity in the dynamical model. What DPAD does is visualized as separating the overall brain activity into distinct pieces related to specific behaviors and discovering how these pieces fit together to build the overall activity.
Here is the Sani et al. abstract:
Understanding the dynamical transformation of neural activity to behavior requires new capabilities to nonlinearly model, dissociate and prioritize behaviorally relevant neural dynamics and test hypotheses about the origin of nonlinearity. We present dissociative prioritized analysis of dynamics (DPAD), a nonlinear dynamical modeling approach that enables these capabilities with a multisection neural network architecture and training approach. Analyzing cortical spiking and local field potential activity across four movement tasks, we demonstrate five use-cases. DPAD enabled more accurate neural–behavioral prediction. It identified nonlinear dynamical transformations of local field potentials that were more behavior predictive than traditional power features. Further, DPAD achieved behavior-predictive nonlinear neural dimensionality reduction. It enabled hypothesis testing regarding nonlinearities in neural–behavioral transformation, revealing that, in our datasets, nonlinearities could largely be isolated to the mapping from latent cortical dynamics to behavior. Finally, DPAD extended across continuous, intermittently sampled and categorical behaviors. DPAD provides a powerful tool for nonlinear dynamical modeling and investigation of neural–behavioral data.
