### Abstract

Despite their success-story, artificial neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more as a mysterious "black box". Although much research has already been done to "open the box," there is a notable hiatus in known publications on analysis of neural networks. So far, mainly sensitivity analysis and rule extraction methods have been used to analyze neural networks. However, these can only be applied in a limited subset of the problem domains where neural network solutions are encountered. In this paper we propose a wider applicable method which, for a given problem domain, involves identifying basic functions with which users in that domain are already familiar, and describing trained neural networks, or parts thereof, in terms of those basic functions. This will provide a comprehensible description of the neural network's function and, depending on the chosen base functions, it may also provide an insight into the neural network' s inner "reasoning." It could further be used to optimize neural network systems. An analysis in terms of base functions may even make clear how to (re)construct a superior system using those base functions, thus using the neural network as a construction advisor.

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

Title of host publication | 3rd IEEE Benelux Signal Processing Symposium (SPS-2002) |

Place of Publication | Leuven, Belgium |

Publisher | Katholieke Universiteit |

Pages | 237-240 |

Number of pages | 4 |

Publication status | Published - Mar 2002 |

Event | 3rd IEEE Benelux Signal Processing Symposium, SPS-2002 - Leuven, Belgium Duration: 21 Mar 2002 → 22 Mar 2002 Conference number: 3 |

### Conference

Conference | 3rd IEEE Benelux Signal Processing Symposium, SPS-2002 |
---|---|

Abbreviated title | SPS |

Country | Belgium |

City | Leuven |

Period | 21/03/02 → 22/03/02 |

## Fingerprint Dive into the research topics of 'Analysis of neural networks in terms of domain functions'. Together they form a unique fingerprint.

## Cite this

van der Zwaag, B. J., Slump, C., & Spaanenburg, L. (2002). Analysis of neural networks in terms of domain functions. In

*3rd IEEE Benelux Signal Processing Symposium (SPS-2002)*(pp. 237-240). Leuven, Belgium: Katholieke Universiteit.