-
dx / dt = Ax, t0=0, t1=1, x(t1)=[1, 1]， A = [[1, 2],[-2, 1]] -- find x(0) = [?, ?]
-
dx / dt = Ax, x(t1)=[1, 1], find t0=?,t1=?,A=?
-
dx / dt = Ax = f_{NN}(x), x(t1)=[1, 1] , t0=?,t1=?,f's parameters=?
-
Continuous Normalizing Flows
[1] Ricky T. Q. Chen, Yulia Rubanova, Jesse Bettencourt, David Duvenaud. "Neural Ordinary Differential Equations." Advances in Neural Information Processing Systems. 2018. [arxiv]