An algorithm for fast convergence in training neural networks
Bogdan M. Wilamowski, Serdar İplikçi, Okyay Kaynak, Mehmet Önder Efe · 2002
In this work, two modifications on Levenberg-Marquardt (LM) algorithm for feedforward neural networks are studied. One modification is made on performance index, while the other one is on calculating gradient information. The modified algorithm gives a better convergence rate compared to the standard LM method and is less computationally intensive and requires less memory. The performance of the algorithm has been checked on several example problems.