Learning state space trajectories in recurrent neural networks : a preliminary report.

Abstract: "We describe a procedure for finding [formula] where E is an arbitrary functional of the temporal trajectory of the states of a continuous recurrent network and w[subscript ij] are the weights of that network. An embellishment of this procedure involving only computations that go forward in time is also described. Computing these quantities allows one to perform gradient descent in the weights to minimize E, so our procedure forms the kernel of a new connectionist learning algorithm."