### Abstract

Traditional neural network training techniques do not work well on problems with many discontinuities, such as those that arise in multicomputer communication cost modeling. We develop a new algorithm to solve this problem. This algorithm incrementally adds modules to the network, successively expanding the 'window' in the data space where the current module works well. The need for a new module is automatically recognized by the system. This algorithm performs very well on problems with many discontinuities, and requires fewer computations than traditional backpropagation.

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

Title of host publication | IEEE International Conference on Neural Networks - Conference Proceedings |

Publisher | IEEE Computer Society |

Pages | 2191-2196 |

Number of pages | 6 |

Volume | 4 |

State | Published - 1994 |

Event | Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA Duration: Jun 27 1994 → Jun 29 1994 |

### Other

Other | Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) |
---|---|

City | Orlando, FL, USA |

Period | 6/27/94 → 6/29/94 |

### ASJC Scopus subject areas

- Software

## Fingerprint Dive into the research topics of 'Incremental network construction algorithm for approximating discontinuous functions'. Together they form a unique fingerprint.

## Cite this

Lee, H., Mehrotra, K., Mohan, C. K., & Ranka, S. (1994). Incremental network construction algorithm for approximating discontinuous functions. In

*IEEE International Conference on Neural Networks - Conference Proceedings*(Vol. 4, pp. 2191-2196). IEEE Computer Society.