Learning Collective Dynamics with Differentiable Gaussian Representations
Differentiable Gaussian Dynamics (DGD) is introduced, which learns this connection through three components: a Gaussian mixture representing heterogeneous response propensities, differentiable aggregation of contact intensity and behavioral probabilities, and feedback recurrence that updates subsequent responses.
Jian-Xiang Ma, Ming-Fu Zhang, Xiaocui Yang et al.
· 0 citations