Authors
Chung-Ming Kuan, Kurt Hornik, Halbert White
Publication date
1994/5
Journal
Neural Computation
Volume
6
Issue
3
Pages
420-440
Publisher
MIT Press
Description
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.
Total citations
Scholar articles
CM Kuan, K Hornik, H White - Neural Computation, 1994