### Abstract

An evaluation is made of several neural network classifiers, comparing their performance on a typical problem, namely handwritten digit recognition. For this purpose, the authors use a database of handwritten digits, with relatively uniform handwriting styles. The authors propose a novel of way of organizing the network architectures by training several small networks so as to deal separately with subsets of the problem, and then combining the results. This approach works in conjunction with various techniques including: layered networks with one or several layers of adaptive connections, fully connected recursive networks, ad hoc networks with no adaptive connections, and architectures with second-degree polynomial decision surfaces.

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

Title of host publication | IJCNN Int Jt Conf Neural Network |

Editors | Anon |

Publisher | Publ by IEEE |

Pages | 127-132 |

Number of pages | 6 |

State | Published - 1989 |

Event | IJCNN International Joint Conference on Neural Networks - Washington, DC, USA Duration: Jun 18 1989 → Jun 22 1989 |

### Other

Other | IJCNN International Joint Conference on Neural Networks |
---|---|

City | Washington, DC, USA |

Period | 6/18/89 → 6/22/89 |

### Fingerprint

### ASJC Scopus subject areas

- Engineering(all)

### Cite this

*IJCNN Int Jt Conf Neural Network*(pp. 127-132). Publ by IEEE.

**Comparing different neural network architectures for classifying handwritten digits.** / Guyon, I.; Poujaud, I.; Personnaz, L.; Dreyfus, G.; Denker, J.; LeCun, Yann.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*IJCNN Int Jt Conf Neural Network.*Publ by IEEE, pp. 127-132, IJCNN International Joint Conference on Neural Networks, Washington, DC, USA, 6/18/89.

}

TY - GEN

T1 - Comparing different neural network architectures for classifying handwritten digits

AU - Guyon, I.

AU - Poujaud, I.

AU - Personnaz, L.

AU - Dreyfus, G.

AU - Denker, J.

AU - LeCun, Yann

PY - 1989

Y1 - 1989

N2 - An evaluation is made of several neural network classifiers, comparing their performance on a typical problem, namely handwritten digit recognition. For this purpose, the authors use a database of handwritten digits, with relatively uniform handwriting styles. The authors propose a novel of way of organizing the network architectures by training several small networks so as to deal separately with subsets of the problem, and then combining the results. This approach works in conjunction with various techniques including: layered networks with one or several layers of adaptive connections, fully connected recursive networks, ad hoc networks with no adaptive connections, and architectures with second-degree polynomial decision surfaces.

AB - An evaluation is made of several neural network classifiers, comparing their performance on a typical problem, namely handwritten digit recognition. For this purpose, the authors use a database of handwritten digits, with relatively uniform handwriting styles. The authors propose a novel of way of organizing the network architectures by training several small networks so as to deal separately with subsets of the problem, and then combining the results. This approach works in conjunction with various techniques including: layered networks with one or several layers of adaptive connections, fully connected recursive networks, ad hoc networks with no adaptive connections, and architectures with second-degree polynomial decision surfaces.

UR - http://www.scopus.com/inward/record.url?scp=0024944137&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024944137&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0024944137

SP - 127

EP - 132

BT - IJCNN Int Jt Conf Neural Network

A2 - Anon, null

PB - Publ by IEEE

ER -