Training feedforward networks with the Marquardt algorithm Export

@article{HaganMenhaj_TNN94, abstract = {The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either of the other techniques when the network contains no more than a few hundred weights}, author = {Hagan, M. T. and Menhaj, M. B.}, booktitle = {Neural Networks, IEEE Transactions on}, citeulike-article-id = {3039952}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/72.329697}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=329697}, doi = {10.1109/72.329697}, journal = {Neural Networks, IEEE Transactions on}, keywords = {artificial\_neural\_networks, learning\_networks}, number = {6}, pages = {989--993}, posted-at = {2008-07-24 15:25:53}, priority = {0}, title = {Training feedforward networks with the Marquardt algorithm}, url = {http://dx.doi.org/10.1109/72.329697}, volume = {5}, year = {1994} }

TY - JOUR ID - HaganMenhaj_TNN94 L3 - citeulike-article-id:3039952 N2 - The Marquardt algorithm for nonlinear least squares is presented and is incorporated into the backpropagation algorithm for training feedforward neural networks. The algorithm is tested on several function approximation problems, and is compared with a conjugate gradient algorithm and a variable learning rate algorithm. It is found that the Marquardt algorithm is much more efficient than either of the other techniques when the network contains no more than a few hundred weights IS - 6 JF - Neural Networks, IEEE Transactions on EP - 993 TI - Training feedforward networks with the Marquardt algorithm VL - 5 T2 - Neural Networks, IEEE Transactions on SP - 989 KW - artificial_neural_networks KW - learning_networks AU - Hagan, MT AU - Menhaj, MB PY - 1994/// UR - http://dx.doi.org/10.1109/72.329697 ER -