Efficient algorithm for training neural networks with one hidden layer
Bogdan M. Wilamowski, Yixin Chen, Aleksander Malinowski · 2003
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.