A Spacetime Perspective on Dynamical Computation in Neural Information Processing Systems
Illustration of the fundamental mathematical difference between standing waves and traveling waves, which are not `spacetime separable’. We suggest these inseparable dynamics in neural activity may have a fundamental role in efficient and generalizable computation.
There is now substantial evidence for traveling waves and other structured spatiotemporal recurrent neural dynamics in cortical structures; but these observations have typically been difficult to reconcile with notions of topographically organized selectivity and feedforward receptive fields. We introduce a new ‘spacetime’ perspective on neural computation in which structured selectivity and dynamics are not contradictory but instead are complimentary. We show that spatiotemporal dynamics may be a mechanism by which natural neural systems encode approximate visual, temporal, and abstract symmetries of the world as conserved quantities, thereby enabling improved generalization and long-term working memory.
T. Anderson Keller, Lyle Muller, Terrence Sejnowski, and Max Welling
Preprint (under review): https://arxiv.org/abs/2409.13669