Free Online Productivity Tools
i2Speak
i2Symbol
i2OCR
iTex2Img
iWeb2Print
iWeb2Shot
i2Type
iPdf2Split
iPdf2Merge
i2Bopomofo
i2Arabic
i2Style
i2Image
i2PDF
iLatex2Rtf
Sci2ools

ALT

2004

Springer

2004

Springer

A revision algorithm is a learning algorithm that identiﬁes the target concept, starting from an initial concept. Such an algorithm is considered eﬃcient if its complexity (in terms of the resource one is interested in) is polynomial in the syntactic distance between the initial and the target concept, but only polylogarithmic in the number of variables in the universe. We give eﬃcient revision algorithms in the model of learning with equivalence and membership queries. The algorithms work in a general revision model where both deletion and addition type revision operators are allowed. In this model one of the main open problems is the eﬃcient revision of Horn sentences. Two revision algorithms are presented for special cases of this problem: for depth-1 acyclic Horn sentences, and for deﬁnite Horn sentences with unique heads. We also present an eﬃcient revision algorithm for threshold functions.

Related Content

Added |
15 Mar 2010 |

Updated |
15 Mar 2010 |

Type |
Conference |

Year |
2004 |

Where |
ALT |

Authors |
Judy Goldsmith, Robert H. Sloan, Balázs Szörényi, György Turán |

Comments (0)