Title | ||
---|---|---|
Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network |
Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/IJCNN.2013.6707004 | Neural Networks |
Keywords | Field | DocType |
conjugate gradient methods,learning (artificial intelligence),neural nets,HONEST network,Levenberg-Marquardt methods,high order neural network,learning methods,resilient propagation,scaled conjugate gradient methods | Conjugate gradient method,Feedforward neural network,Exponential function,Computer science,Artificial intelligence,Artificial neural network,Machine learning,Test set,Levenberg–Marquardt algorithm | Conference |
ISSN | ISBN | Citations |
2161-4393 | 978-1-4673-6128-6 | 0 |
PageRank | References | Authors |
0.34 | 11 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Islam El-Nabarawy | 1 | 3 | 2.09 |
Ashraf M. Abdelbar | 2 | 243 | 25.43 |
Wunsch II Donald C. | 3 | 1354 | 91.73 |