Monthly
288 pp. per issue
6 x 9, illustrated
ISSN
0899-7667
E-ISSN
1530-888X
2014 Impact factor:
2.21

Neural Computation

May 1994, Vol. 6, No. 3, Pages 420-440
(doi: 10.1162/neco.1994.6.3.420)
© 1994 Massachusetts Institute of Technology
A Convergence Result for Learning in Recurrent Neural Networks
Article PDF (778.89 KB)
Abstract

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.