### Abstract

Evaluation of the bound requires knowledge of a priori probabilities and of the class-condi-tional probability density functions. A tighter bound is obtained for the case of equal a priori probabilities, and a further bound is obtained that is independent of the a priori probabilities. An upper bound on the probability of error for the general pattern recognition problem is obtained as a functional of the pairwise Kolmogorov variational distances.

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

Pages (from-to) | 943-944 |

Number of pages | 2 |

Journal | IEEE Transactions on Computers |

Volume | C-20 |

Issue number | 8 |

DOIs | |

State | Published - Jan 1 1971 |

### Fingerprint

### ASJC Scopus subject areas

- Software
- Theoretical Computer Science
- Hardware and Architecture
- Computational Theory and Mathematics

### Cite this

**Some Upper Bounds on Error Probability for Multiclass Pattern Recognition.** / Toussaint, Godfried.

Research output: Contribution to journal › Article

*IEEE Transactions on Computers*, vol. C-20, no. 8, pp. 943-944. https://doi.org/10.1109/T-C.1971.223380

}

TY - JOUR

T1 - Some Upper Bounds on Error Probability for Multiclass Pattern Recognition

AU - Toussaint, Godfried

PY - 1971/1/1

Y1 - 1971/1/1

N2 - Evaluation of the bound requires knowledge of a priori probabilities and of the class-condi-tional probability density functions. A tighter bound is obtained for the case of equal a priori probabilities, and a further bound is obtained that is independent of the a priori probabilities. An upper bound on the probability of error for the general pattern recognition problem is obtained as a functional of the pairwise Kolmogorov variational distances.

AB - Evaluation of the bound requires knowledge of a priori probabilities and of the class-condi-tional probability density functions. A tighter bound is obtained for the case of equal a priori probabilities, and a further bound is obtained that is independent of the a priori probabilities. An upper bound on the probability of error for the general pattern recognition problem is obtained as a functional of the pairwise Kolmogorov variational distances.

UR - http://www.scopus.com/inward/record.url?scp=0015112303&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0015112303&partnerID=8YFLogxK

U2 - 10.1109/T-C.1971.223380

DO - 10.1109/T-C.1971.223380

M3 - Article

AN - SCOPUS:0015112303

VL - C-20

SP - 943

EP - 944

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

SN - 0018-9340

IS - 8

ER -