Title :
Efficient algorithm for training neural networks with one hidden layer
Author :
Wilamowski, Bogdan M. ; Chen, Yixin ; Malinowski, Aleksander
Author_Institution :
Dept. of EE, Wyoming Univ., Laramie, WY, USA
Abstract :
Efficient second order algorithm for training feedforward neural networks is presented. The algorithm has a similar convergence rate as the Lavenberg-Marquardt (LM) method and it is less computationally intensive and requires less memory. This is especially important for large neural networks where the LM algorithm becomes impractical. Algorithm was verified with several examples
Keywords :
computational complexity; convergence; feedforward neural nets; learning (artificial intelligence); multilayer perceptrons; computational complexity; convergence rate; efficient second-order algorithm; feedforward neural network training; hidden neural layer; modified Lavenberg-Marquardt method; modified Levenberg-Marquardt method; Backpropagation algorithms; Convergence; Equations; Feedforward neural networks; Jacobian matrices; Neural networks; Neurons; Performance analysis; Stability; Stochastic processes;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.832636
