๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

An improved training algorithm for feedforward neural network learning based on terminal attractors

โœ Scribed by Xinghuo Yu; Bin Wang; Batsukh Batbayar; Liuping Wang; Zhihong Man


Publisher
Springer US
Year
2010
Tongue
English
Weight
592 KB
Volume
51
Category
Article
ISSN
0925-5001

No coin nor oath required. For personal study only.


๐Ÿ“œ SIMILAR VOLUMES


Training Feedforward Neural Networks: An
โœ Charles W. Lee ๐Ÿ“‚ Article ๐Ÿ“… 1997 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 711 KB

An algorithm is derived for supervised training in mtdtilayer feedforwardneural networks. Relative to the gradient descent backpropagation algorithm it appears to give bothfaster convergence and improved generalization, whilst preserving the system of backpropagating errors throughthe network.