On aggregating teams of learning machines

The paper investigates for which success ratios can a team be replaced by a single machine without any loss in learning power. The answer depends on the concepts being learned and the criteria of success employed. The minimum cut off ratio where a team can be replaced by a single machine is referred to as the aggregation ratio of the criterion. Aggregation ratios can be derived for finite identification of languages from positive data and for numerous criteria involving language learning from both positive and negative data.