Sciweavers

Share
IJCNN
2007
IEEE

TRUST-TECH Based Neural Network Training

10 years 9 months ago
TRUST-TECH Based Neural Network Training
— Efficient Training in a neural network plays a vital role in deciding the network architecture and the accuracy of these classifiers. Most popular local training algorithms tend to be greedy and hence get stuck at the nearest local minimum of the error surface and this corresponds to suboptimal network model. Stochastic approaches in combination with local methods are used to obtain an effective set of training parameters. Due to the lack of effective fine-tuning capability, these algorithms often fail to obtain such an optimal set of parameters and are computationally expensive. As a trade-off between computational expense and accuracy required, a novel method to improve the local search capability of training algorithms is proposed in this paper. This approach takes advantage of TRUST-TECH (TRansformation Under STability-reTaining Equilibrium CHaracterization) to compute neighborhood local minima on the error surface surrounding the current solution in a systematic manner. Emp...
Hsiao-Dong Chiang, Chandan K. Reddy
Added 03 Jun 2010
Updated 03 Jun 2010
Type Conference
Year 2007
Where IJCNN
Authors Hsiao-Dong Chiang, Chandan K. Reddy
Comments (0)
books