Multiple-start directed search for improved NN solution

We propose a new technique to improve the confidence in results of repeated neural network training runs under the practical constraint of a fixed computational budget. Our technique is applicable to problems for which there is a correlation between results early in the training process and results near the end of training. Targeting well-studied training problems, the technique may be most valuable when the computational time required for thorough training makes impractical performing a large number of differently initialized training sessions.