### Abstract

A two class pattern recognition algorithm is introduced for learning the optimal separating function within a given finite dimensional linear space of functions. It is proved that the algorithm converges with probability one to the separating function minimizing the probability of misclassification over the given class. This stochastic gradient process is based on asymptotically unbiased estimates of the gradient vector of error probability. This method is proposed. to improve classification rules obtained by other methods.

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

Pages (from-to) | 371-382 |

Number of pages | 12 |

Journal | Probl Control Inf Theory |

Volume | 5 |

Issue number | 4 |

Publication status | Published - Jan 1 1976 |

### ASJC Scopus subject areas

- Engineering(all)

## Fingerprint Dive into the research topics of 'ON THE MINIMIZATION OF CLASSIFICATION ERROR PROBABILITY IN STATISTICAL PATTERN RECOGNITION.'. Together they form a unique fingerprint.

## Cite this

Fritz, J., & Gyorfi, L. (1976). ON THE MINIMIZATION OF CLASSIFICATION ERROR PROBABILITY IN STATISTICAL PATTERN RECOGNITION.

*Probl Control Inf Theory*,*5*(4), 371-382.