Explanation facility for neural networks |
| |
| Authors: | L. F. Pau T. Götzsche |
| |
| Affiliation: | (1) Technical University of Denmark, Bldg. 348/EMI, DK-2800 Lyngby, Denmark;(2) Present address: Digital Equipment Europe, PO Box 129, F 06561 Valbonne, France;(3) Present address: IBM Danmark A/S, Denmark |
| |
| Abstract: | ![]()
This paper give a methodology, PROLOG code, as well as an example of an explanation facility EN applicable to most neural networks. It involves How?, Why? and TRACE facilities, and is based on a general explanation degree calculation in a multilayer neural network, as well as on input node characterization grammars for synthesis of explanation text. |
| |
| Keywords: | Neural networks explanation facilities Prolog input characterization grammar text generation |
| 本文献已被 SpringerLink 等数据库收录！ |
|
