A note on batch and incremental learnability (Q1271611): Difference between revisions

The author presents the result that the collections of recursively enumerable languages those are finite identified from both the positive and the negative data can also be identified in the limit only from the positive data by giving an algorithmic transformation on machines. This transformation also yields an algorithm to convert a batch learning system that learns from both positive and negative data into an incremental learning system that learns from the positive data only.