Abstract.
A stability criterion for learning is given. In the case of learning-rate adaptation of backpropagation, a class of asymptotically stable algorithms is presented and studied, including a convergence proof. Simulations demonstrate relevance and limitations.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received January 29, 1997; revised June 19, 1997.
Rights and permissions
About this article
Cite this article
Rüger, S. A Class of Asymptotically Stable Algorithms for Learning-Rate Adaptation . Algorithmica 22, 198–210 (1998). https://doi.org/10.1007/PL00013830
Issue Date:
DOI: https://doi.org/10.1007/PL00013830