Minimisation of data collection by active learning

Uses the `query-by-committee´ approach for building an active scheme for data collection. In this method data gathering is reduced to a minimum, yet modelling accuracy is uncompromised. The authors´ active querying criterion is determined by whether or not several models agree when they are fitted to random subsamples of a small amount of collected data. Experiments with neural network models to establish the feasibility of the authors´ algorithm have produced encouraging results