### 摘要

To enhance the generalization of neural network model, we proposed a novel neural network, Minimum Risk Neural Networks (MRNN), whose principle is the combination of minimizing the sum of squares of error and maximizing the classification margin, based on the principle of structural risk minimization. Therefore, the objective function of MRNN is the combination of the sum of squared error and the sum of squares of the slopes of the classification function. Besides, we derived a more sophisticated formula similar to the traditional weight decay technique from the MRNN, establishing a more rigorous theoretical basis for the technique. This study employed several real application examples to test the MRNN. The results led to the following conclusions. (1) As long as the penalty coefficient was in the appropriate range, MRNN performed better than pure MLP. (2) MRNN may perform better in difficult classification problems than MLP using weight decay technique.

原文 | English |
---|---|

主出版物標題 | Emerging Intelligent Computing Technology and Applications - 8th International Conference, ICIC 2012, Proceedings |

頁面 | 10-16 |

頁數 | 7 |

DOIs | |

出版狀態 | Published - 2012 八月 20 |

事件 | 8th International Conference on Emerging Intelligent Computing Technology and Applications, ICIC 2012 - Huangshan, China 持續時間: 2012 七月 25 → 2012 七月 29 |

### 出版系列

名字 | Communications in Computer and Information Science |
---|---|

卷 | 304 CCIS |

ISSN（列印） | 1865-0929 |

### Other

Other | 8th International Conference on Emerging Intelligent Computing Technology and Applications, ICIC 2012 |
---|---|

國家 | China |

城市 | Huangshan |

期間 | 12-07-25 → 12-07-29 |

### All Science Journal Classification (ASJC) codes

- Computer Science(all)
- Mathematics(all)

## 指紋 深入研究「Minimum risk neural networks and weight decay technique」主題。共同形成了獨特的指紋。

## 引用此

*Emerging Intelligent Computing Technology and Applications - 8th International Conference, ICIC 2012, Proceedings*(頁 10-16). (Communications in Computer and Information Science; 卷 304 CCIS). https://doi.org/10.1007/978-3-642-31837-5_2