Talk:Algorithmic learning theory

I think this article erroneously states that "Gold showed that any language which is defined by a Turing machine program can be learned in the limit by another Turing-complete machine using enumeration." (Or it least this is extremely misleading.) Specifically, the only way that recursive (and recursively enumerable) languages are learnable in Gold's "Language Identification in the Limit" paper is if the learner is presented with text generated by a primitive recursive enumeration of the target language and the learner is only required to name the hypothesis language by a (recursively enumerable) generator. Davidslv 05:25, 11 December 2005 (UTC)Davidslv