Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network
Computer Science & Engineering Department
The HONEST network is a high order neural network that uses product units and adaptable exponential weights. In this paper, we explore the use of several learning methods with the HONEST network: Levenberg-Marquardt (LM), Conjugate Gradient (CG), Scaled Conjugate Gradient (a technique that combines LM and CG), and resilient propagation (RP). Using a benchmark of 19 datasets, we find that the first three methods mentioned produce lower average test set errors than RP to a statistically significant extent. © 2013 IEEE.
Proceedings of the International Joint Conference on Neural Networks
Dallas, TX, USA
(2013).Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network. IEEE. , 2123-2129
El-Nabarawy, Islam, et al.
Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network. IEEE, 2013.pp. 2123-2129