The problem of the pattern selection strategy for neural network train
ing has not yet received much attention. In back propagation training
all patterns are usually presented equally often in random order This
paper presents and compares several alternative pattern selection stra
tegies that adapt to the training process. They favor the selection of
patterns producing high error values to the disadvantage of the patte
rns already mastered by the network. The strategies presented are of t
wo types, random and deterministic. In a random strategy, a pattern is
selected randomly with some variable probability depending on the sta
te of the training process. In contrast, the deterministic strategies
follow predefined, global schemes that increase the presentation frequ
ency of certain patterns by forced repetition. Simulation results for
two test problems show that convergence time and learning accuracy can
be improved, but only by strategies of the deterministic type.