Most neural network hydrological modelling has used split-sample validation to ensure good out-of-sample generalisation and thus safeguard each potential solution against the danger of overfitting. However, given that each sub-set is required to provide a comprehensive and sufficient representation of both environmental inputs and hydrological processes, then to partition the data could create limited individual representations that are, in some manner or other, deficient with respect to fitness-for-purpose. To address this issue a comparison has been undertaken between neural network rainfall-runoff models developed using (a) conventional stopping conditions and (b) a continuous single-model bootstrap. The results exhibit marginal improvement in terms of greater accuracies and better global generalisations—but the operation itself demonstrates substantial benefits through the provision of additional diagnostic capabilities and increased automation with respect to certain problematic aspects of the model development process.