Variable Step Search Algorithm for MLP Training

M. Kordos (Poland) and W. Duch (Poland, Singapore)


neural networks, learning algorithms, MLP, search algorithms


The variable step search algorithm is based on a simple search procedure that changes one network parameter at a time. Visualization of learning trajectories and MLP error surfaces is used for the algorithm design and optimization. The algorithm is compared to three other MLP training algorithms: Levenberg-Marquardt, scaled conjugate gradient, and training based on numerical gradient.

Important Links:

Go Back