## Abstract

In this paper we study a Bayesian or average-case model of concept learning with a twofold goal: to provide more precise characterizations of learning curve (sample complexity) behavior that depend on properties of both the prior distribution over concepts and the sequence of instances seen by the learner, and to smoothly unite in a common framework the popular statistical physics and VC dimension theories of learning curves. To achieve this, we undertake a systematic investigation and comparison of two fundamental quantities in learning and information theory: the probability of an incorrect prediction for an optimal learning algorithm, and the Shannon information gain. This study leads to a new understanding of the sample complexity of learning in several existing models.

Original language | English (US) |
---|---|

Pages (from-to) | 83-113 |

Number of pages | 31 |

Journal | Machine Learning |

Volume | 14 |

Issue number | 1 |

DOIs | |

State | Published - Jan 1994 |

## All Science Journal Classification (ASJC) codes

- Software
- Artificial Intelligence

## Keywords

- average-case learning
- Bayesian learning
- information theory
- learning curves
- statistical physics
- VC dimension