On Conservative Learning of R.e. Languages

Partially conservative learning is a variant of partial learning whereby the learner, on a text for a target language L, outputs one index e with L = We infinitely often and every further hypothesis d is output only finitely often and satisfies L 6⊆ Wd. The present paper studies the learning strength of this notion, comparing it with other learnability criteria such as confident partial learning, explanatory learning, as well as behaviourally correct learning. It is further established that for classes comprising infinite sets, partially conservative learnability is in fact equivalent to explanatory learnability relative to the halting problem. 1998 ACM Subject Classification Dummy classification