A Convergence Result for Learning in Recurrent Neural Networks
Chung‐Ming Kuan, Kurt Hornik, Halbert White · Neural Computation · 1994
We give a rigorous analysis of the convergence properties of a backpropagation algorithm for recurrent networks containing either output or hidden layer recurrence. The conditions permit data generated by stochastic processes with considerable dependence. Restrictions are offered that may help assure convergence of the network parameters to a local optimum, as some simulations illustrate.