Adaptive stepsize algorithms for on-line
β
G.D. Magoulas; V.P. Plagianakos; M.N. Vrahatis
π
Article
π
2001
π
Elsevier Science
π
English
β 312 KB
In this paper a method for adapting the stepsize in on-line network training is presented. The proposed technique derives from the stochastic gradient descent proposed by Almeida et al. [On-line Learning in Neural Networks, 111-134, Cambridge University Press, 1998]. The new aspect of our approach c