### Abstract

The learnability of the class of exclusive-or expansions based on monotone DNF formulas is investigated. The class consists of the formulas of the form f = f_{1} ⊕⋯⊕ f_{d}, where f_{1} > ⋯ > f_{d} are monotone DNF formulas. It is shown that any Boolean function can be represented as a formula in this class, and that the representation in the simplest form is unique. Learning algorithms that learn such formulas using various queries are presented: An algorithm with subset and superset queries and one with membership and equivalence queries are given. The former can learn any formula in the class, while the latter is proved to learn formulas of constant depth, i.e., formulas represented as exclusive-or of a constant number of monotone DNF formulas. In spite of the seemingly strong restriction of the depth being constant, the class of formulas of constant depth includes functions with very high complexity in terms of DNF and CNF representations, so the latter algorithm could learn Boolean functions significantly complex otherwise represented.

Original language | English |
---|---|

Pages (from-to) | 37-50 |

Number of pages | 14 |

Journal | Theoretical Computer Science |

Volume | 241 |

Issue number | 1-2 |

DOIs | |

Publication status | Published - 2000 Jun 28 |

Externally published | Yes |

### ASJC Scopus subject areas

- Theoretical Computer Science
- Computer Science(all)

## Fingerprint Dive into the research topics of 'The learnability of exclusive-or expansions based on monotone DNF formulas'. Together they form a unique fingerprint.

## Cite this

*Theoretical Computer Science*,

*241*(1-2), 37-50. https://doi.org/10.1016/S0304-3975(99)00265-0