Part of Advances in Neural Information Processing Systems 2 (NIPS 1989)
A simple method for training the dynamical behavior of a neu(cid:173) ral network is derived. It is applicable to any training problem in discrete-time networks with arbitrary feedback. The algorithm resembles back-propagation in that an error function is minimized using a gradient-based method, but the optimization is carried out in the hidden part of state space either instead of, or in addition to weight space. Computational results are presented for some simple dynamical training problems, one of which requires response to a signal 100 time steps in the past.