作成者 |
|
本文言語 |
|
出版者 |
|
|
発行日 |
|
収録物名 |
|
巻 |
|
出版タイプ |
|
アクセス権 |
|
関連DOI |
|
|
関連URI |
|
|
関連情報 |
|
|
概要 |
A majority of studies on inductive inference of formal languages and models of logic programings have mainly used Gold's identification in the limit as a correct inference criterion. However, in this ...criterion, we can not decide in general whether the inference terminates or not, and the results of the inference involve some risks. In this paper, we consider the definite inductive inference as a successful identification criterion. The definite inference machine produces a unique guess just once when it convinces the termination of the inference, and the result does not involve any risk at all. We discuss the necessary and sufficient conditions for definite inductive inferability from positive data and complete data respectively.続きを見る
|