## Incremental Learning from Positive Data
Iterative inference can be refined by allowing the learner to store
an Our results are threefold. First, the learning capabilities of the various models of incremental learning are related to previously studied learning models. It is proved that incremental learning can be always simulated by inference devices that are both set-driven and conservative. Second, feed-back learning is shown to be more powerful than iterative inference, and its learning power is incomparable to that of bounded example memory inference which itself extends that of iterative learning, too. In particular, the learning power of bounded example memory always increases if the number of examples the learner is allowed to store is incremented.
Third, a sufficient condition for iterative
inference allowing The results obtained provide strong evidence that there is no unique way to design superior incremental learning algorithms. Instead, incremental learning is the art of knowing what to overlook.
©Copyright 1996, Academic Press. |