Using input parameter influences to support the decisions of feedforward neural networks

Whilst rules extracted from neural networks assist the explanation process, in isolation they do not illustrate the relative importance of each input parameter nor how sensitive the network's output is to these parameters. In this paper we discuss three related measures of input parameter influence which can be used to support explanation facilities for neural networks. An algorithm for generating rules from real-valued networks based on the in i nfluence measures is also presented. (C) 1999 Elsevier Science B.V. All rig hts reserved.