## An analysis of Bayesian classifiers (1992)

### Cached

### Download Links

- [www.cs.iastate.edu]
- [www.isle.org]
- [www.isle.org]
- DBLP

### Other Repositories/Bibliography

Venue: | IN PROCEEDINGS OF THE TENTH NATIONAL CONFERENCE ON ARTI CIAL INTELLIGENCE |

Citations: | 336 - 17 self |

### BibTeX

@INPROCEEDINGS{Langley92ananalysis,

author = {Pat Langley and Wayne Iba and Kevin Thompson},

title = {An analysis of Bayesian classifiers},

booktitle = {IN PROCEEDINGS OF THE TENTH NATIONAL CONFERENCE ON ARTI CIAL INTELLIGENCE},

year = {1992},

pages = {223--228},

publisher = {MIT Press}

}

### Years of Citing Articles

### OpenURL

### Abstract

In this paper we present anaverage-case analysis of the Bayesian classifier, a simple induction algorithm that fares remarkably well on many learning tasks. Our analysis assumes a monotone conjunctive target concept, and independent, noise-free Boolean attributes. We calculate the probability that the algorithm will induce an arbitrary pair of concept descriptions and then use this to compute the probability of correct classification over the instance space. The analysis takes into account the number of training instances, the number of attributes, the distribution of these attributes, and the level of class noise. We also explore the behavioral implications of the analysis by presenting

### Citations

3928 | Pattern Classification and Scene Analysis - Duda, Hart - 1973 |

3364 | Induction on decision trees - Quinlan - 1986 |

750 | The CN2 induction algorithm - Clark, Niblett - 1989 |

741 | Aha, “UCI repository of machine learning data bases,” http: //www.ics.uci.edu/~mlearn/MLRepository.html - Murphy, W - 1992 |

644 | Knowledge acquisition via incremental conceptual clustering - Fisher - 1987 |

270 | Pattern Classi cation and Scene Analysis - Duda, Hart, et al. - 1973 |

241 | AutoClass: A bayesian classification system - Cheeseman, Kelly, et al. - 1988 |

221 | Learning from noisy examples - Angluin, Laird - 1988 |

104 | ASSISTANT 86: A knowledge-elicitation tool for sophisticated users - Cestnik, Kononenko, et al. - 1987 |

67 | A Bayesian Method for Constructing Bayesian Belief Networks from Databases - Cooper, Herskovits - 1991 |

59 | Machine learning as an experimental science - Kibler, Langley - 1988 |

52 | The role of structured induction in expert systems - Shapiro - 1983 |

52 | Concept formation in structured domains - Thompson, Langley |

44 | Induction of one-level decision trees - WI, Langley - 1992 |

40 | Probably Approximately Correct Learning
- Haussler
- 1990
(Show Context)
Citation Context ...al domains in search of empirical regularities (e.g., Kibler & Langley, 1988). Others have focused on theoretical analyses, often within the paradigm of probably approximately correct learning (e.g., =-=Haussler, 1990-=-). However, most experimental studies are based only on informal analyses of the learning task, whereas most formal analyses address the worst case, and thus bear little relation to empirical results.... |

32 | How evaluation guides ai research - Cohen, Howe - 1988 |

32 | Recent results on boolean concept learning - KEARNS, LI, et al. - 1987 |

28 | Learning causal trees from dependence information - Geiger, Paz, et al. - 1990 |

28 | Empirical Learning as a Function of Concept Character - Rendell, Cho - 1990 |

27 | Concept simplification and prediction accuracy - Fisher, Schlimmer - 1988 |

11 | Integrating memory and search in planning - Allen, Langley - 1990 |

10 | Autoclass: A bayesian classi cation system - Cheeseman, Kelly, et al. - 1988 |

5 | Learning to recognize movements - Iba, Gennari - 1991 |

3 | Averagecase analysis of a k-CNF learning algorithm - Hirschberg - 1991 |

3 | Average-case analysis of conjunctive learning algorithms - Pazzani - 1990 |

1 | Introduction to IND and recursive partitioning (Technical Report FIA91-28 - Buntine, Caruana - 1991 |

1 |
Learning to recognize movements
- Gennari
- 1991
(Show Context)
Citation Context ...eb, an incremental algorithm for conceptual clustering that draws heavily on Bayesian ideas, and the literature reports a number of systems that build on this work (e.g., Allen & Langley, 1990; Iba & =-=Gennari, 1991-=-; Thompson & Langley, 1991). Cheeseman et al. (1988) have outlined AutoClass, a nonincremental system that uses Bayesian methods to cluster instances into groups, and other researchers have focused on... |

1 | Calculation of the learning curve of Bayes optimal classification algorithm for learning a perceptron with noise - unknown authors - 1991 |

1 | Introduction to IND and Recursive Partitioning (NASA - Buntine - 1991 |

1 | Induction of one-level decision trees. Unpublished manuscript - Iba - 1992 |

1 | Constructive induction in knowledge-based networks - Towell, Craven - 1991 |

1 | Refinement of approxiBayesian Classifiers 14 mate domain theories by knowledge-based neural networks - Towell, Shavlik - 1990 |

1 | Analysis of Bayesian Classifiers 228 - Cooper, Herskovits - 1991 |

1 | Calculation of the learning curveofBayes optimal classi cation algorithm for learning a perceptron with noise - unknown authors - 1991 |