Learning k-Variable Pattern Languages Efficiently Stochastically Finite on Average from Positive Data

Abstract. The present paper presents a new approach of how to convert Gold-style [4] learning in the limit into stochastically finite learning with high confidence. We illustrate this approach on the concept class of all pattern languages. The transformation of learning in the limit into stochastically finite learning with high confidence is achieved by first analyzing the Lange

• Type: Conference
• Year: 1998
• Where: ICGI
• Authors: Peter Rossmanith, Thomas Zeugmann
• Keywords: Expected Total Learning, ICGI 1998, Natural Language Processing, Pattern Languages, Total Learning Time